wuyang/agent
2
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
df475e8d909e78914be33ce689b94509eafb3e5e
agent/data/research/memory-paper-ledger.csv
T
wuyang ab758e774e Audit recent Agent memory research
2026-07-10 18:52:00 +08:00

166 KiB
Raw Blame History

1arxiv_idpublishedperiodtitleurltitle_centralscreen_relevancescreen_problemscreen_sourcethemestitle_themesevidence_scorematched_queries
22501.139562025-01-202025-H1Zep: A Temporal Knowledge Graph Architecture for Agent Memoryhttps://arxiv.org/abs/2501.13956Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;systems_efficiencyretrieval_representation;systems_efficiency7agent-memory
32501.124852025-01-212025-H1R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memoryhttps://arxiv.org/abs/2501.12485Truecoreupdate_forgettingmodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency4agent-memory
42501.181602025-01-302025-H1RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditinghttps://arxiv.org/abs/2501.18160Falsecoreexecution_statemodelevaluation_diagnosis;systems_efficiency6agent-memory
52502.069752025-02-102025-H1Position: Episodic Memory is the Missing Piece for Long-Term LLM Agentshttps://arxiv.org/abs/2502.06975Truecoreexecution_statemodelretrieval_access;systems_efficiency0episodic-memory
62502.101772025-02-142025-H1STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planninghttps://arxiv.org/abs/2502.10177Truecoreupdate_forgettingmodelrepresentation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal6agent-memory
72502.105502025-02-142025-H1Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learninghttps://arxiv.org/abs/2502.10550Truecorerepresentationmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;experience_skill_policy;execution_multimodal2agent-memory;memory-evaluation
82502.121102025-02-172025-H1A-MEM: Agentic Memory for LLM Agentshttps://arxiv.org/abs/2502.12110Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;systems_efficiency6agent-memory
92502.131722025-02-172025-H1Unveiling Privacy Risks in LLM Agent Memoryhttps://arxiv.org/abs/2502.13172Truecoresecurity_privacymodelsecurity_privacy_trustsecurity_governance2agent-memory
102502.160902025-02-222025-H1Echo: A Large Language Model with Temporal Episodic Memoryhttps://arxiv.org/abs/2502.16090Truecoreexecution_statemodelretrieval_access;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui6episodic-memory
112502.191452025-02-262025-H1Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systemshttps://arxiv.org/abs/2502.19145Falsecoresecurity_privacymodelevaluation_diagnosis;security_privacy_trust;multi_agent_sharedsecurity_governance;personal_shared2agent-memory
122503.037042025-03-052025-H1Memory Injection Attacks on LLM Agents via Query-Only Interactionhttps://arxiv.org/abs/2503.03704Truecoreexecution_statemodelretrieval_access;security_privacy_trust;multimodal_embodied_guisecurity_governance2agent-memory
132503.043922025-03-062025-H1AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Managementhttps://arxiv.org/abs/2503.04392Falsecoresecurity_privacymodelrepresentation_organization;security_privacy_trust;multi_agent_sharedretrieval_representation;personal_shared5agent-memory
142503.217602025-03-272025-H1MemInsight: Autonomous Memory Augmentation for LLM Agentshttps://arxiv.org/abs/2503.21760Truecoreexperience_learningmodelretrieval_access;representation_organization5long-term-memory
152503.235142025-03-302025-H1If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMshttps://arxiv.org/abs/2503.23514Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multi_agent_sharedbenchmark_diagnosis;experience_skill_policy6episodic-memory
162504.092832025-04-122025-H1Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scalehttps://arxiv.org/abs/2504.09283Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosisupdate_forgetting2agent-memory
172504.169462025-04-182025-H1MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulationhttps://arxiv.org/abs/2504.16946Falsecoreexperience_learningmodelevaluation_diagnosis;multimodal_embodied_gui;systems_efficiencysystems_efficiency6agent-memory
182504.152632025-04-212025-H1Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoninghttps://arxiv.org/abs/2504.15263Truecoreexperience_learningmodelevaluation_diagnosis;multimodal_embodied_gui5long-term-memory
192504.201172025-04-282025-H1ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologieshttps://arxiv.org/abs/2504.20117Falsecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosis;multi_agent_sharedretrieval_representation;personal_shared7long-term-memory
202505.004722025-05-012025-H1UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaceshttps://arxiv.org/abs/2505.00472Truecoreupdate_forgettingmodelexperience_skill_learning;security_privacy_trust;multimodal_embodied_gui;systems_efficiency2agent-memory
212505.051772025-05-082025-H1MARK: Memory Augmented Refinement of Knowledgehttps://arxiv.org/abs/2505.05177Truecoreupdate_forgettingmodelretrieval_access;representation_organization;systems_efficiencysystems_efficiency1agent-memory
222505.129232025-05-192025-H1The Traitors: Deception and Trust in Multi-Agent Language Model Simulationshttps://arxiv.org/abs/2505.12923Falsecoreexperience_learningmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_sharedsecurity_governance;personal_shared2long-term-memory
232505.139412025-05-202025-H1MLZero: A Multi-Agent System for End-to-end Machine Learning Automationhttps://arxiv.org/abs/2505.13941Falsecoreupdate_forgettingmodelevaluation_diagnosis;multi_agent_shared;multimodal_embodied_guiexperience_skill_policy;personal_shared5episodic-memory
242505.141632025-05-202025-H1DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulationhttps://arxiv.org/abs/2505.14163Falsecoreexperience_learningmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;systems_efficiency6long-term-memory
252505.160672025-05-212025-H1How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorhttps://arxiv.org/abs/2505.16067Truecoreexperience_learningmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;experience_skill_policy3agent-memory
262505.163482025-05-222025-H1Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilizationhttps://arxiv.org/abs/2505.16348Truecoreexperience_learningmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal;personal_shared4agent-memory;episodic-memory
272505.182792025-05-232025-H1Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Controlhttps://arxiv.org/abs/2505.18279Truesupportingshared_memorymodelrepresentation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencypersonal_shared0long-term-memory
282505.192372025-05-252025-H1Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robotshttps://arxiv.org/abs/2505.19237Falsecorerepresentationmodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal1episodic-memory
292505.194362025-05-262025-H1Task Memory Engine: Spatial Memory for Robust Multi-Step LLM Agentshttps://arxiv.org/abs/2505.19436Truecorerepresentationmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;security_privacy_trustexecution_multimodal7long-term-memory
302505.202312025-05-262025-H1MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agentshttps://arxiv.org/abs/2505.20231Truesupportingrepresentationmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal4long-term-memory
312505.226572025-05-282025-H13DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Modelhttps://arxiv.org/abs/2505.22657Truecorerepresentationmodelexecution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal7episodic-memory
322506.014422025-06-022025-H1Agentic Episodic Controlhttps://arxiv.org/abs/2506.01442Falsecorerepresentationmodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiency5episodic-memory
332506.019362025-06-022025-H1Should Decision-Makers Reveal Classifiers in Online Strategic Classification?https://arxiv.org/abs/2506.01936Falsesupportingrepresentationmodel2agent-memory
342506.073982025-06-092025-H1G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemshttps://arxiv.org/abs/2506.07398Truecorerepresentationmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_guiretrieval_representation;personal_shared3agent-memory
352506.120882025-06-102025-H1Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Financial Trust and Compliance, Cybersecurity, Privacy & AI Safety: A Comprehensive Survey, Roadmap & Implementation Blueprinthttps://arxiv.org/abs/2506.12088Falseperipheralsecurity_privacymodelevaluation_diagnosis;security_privacy_trust;multimodal_embodied_guibenchmark_diagnosis;security_governance3agent-memory
362506.173182025-06-182025-H1Context manipulation attacks : Web agents are susceptible to corrupted memoryhttps://arxiv.org/abs/2506.17318Truesupportingrepresentationmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiexecution_multimodal;security_governance5agent-memory
372506.173382025-06-192025-H1PBFT-Backed Semantic Voting for Multi-Agent Memory Pruninghttps://arxiv.org/abs/2506.17338Truesupportingrepresentationmodelretrieval_access;update_forgetting;evaluation_diagnosis;multi_agent_shared;systems_efficiencypersonal_shared4agent-memory
382506.194332025-06-242025-H1Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory Systemhttps://arxiv.org/abs/2506.19433Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal6long-term-memory
392507.022592025-07-03baseline-2025H2-Jan2026MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agenthttps://arxiv.org/abs/2507.02259Truecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;systems_efficiencyexperience_skill_policy2agent-memory
402507.041722025-07-05baseline-2025H2-Jan2026Gathering Teams of Bounded Memory Agents on a Linehttps://arxiv.org/abs/2507.04172Falseperipheralsystems_costmodelmultimodal_embodied_gui0agent-memory
412507.105622025-07-05baseline-2025H2-Jan2026SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agentshttps://arxiv.org/abs/2507.10562Falsecoreupdate_forgettingmodelretrieval_access;security_privacy_trust;multi_agent_shared;systems_efficiency5agent-memory
422507.052572025-07-07baseline-2025H2-Jan2026Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionshttps://arxiv.org/abs/2507.05257Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis2agent-memory
432507.054452025-07-07baseline-2025H2-Jan2026A Systematization of Security Vulnerabilities in Computer Use Agentshttps://arxiv.org/abs/2507.05445Falseperipheralsecurity_privacymodelevaluation_diagnosis;security_privacy_trust;multimodal_embodied_guisecurity_governance2agent-memory
442507.079572025-07-10baseline-2025H2-Jan2026MIRIX: Multi-Agent Memory System for LLM-Based Agentshttps://arxiv.org/abs/2507.07957Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiencypersonal_shared6agent-memory
452507.167132025-07-22baseline-2025H2-Jan2026A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real Worldhttps://arxiv.org/abs/2507.16713Falsecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;execution_multimodal8long-term-memory
462507.229252025-07-23baseline-2025H2-Jan2026Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentshttps://arxiv.org/abs/2507.22925Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation6long-term-memory
472507.214072025-07-29baseline-2025H2-Jan2026Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectshttps://arxiv.org/abs/2507.21407Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;security_privacy_trust;multi_agent_shared;multimodal_embodied_guiretrieval_representation0long-term-memory
482508.000312025-07-30baseline-2025H2-Jan2026Git Context Controller: Manage the Context of LLM-based Agents like Githttps://arxiv.org/abs/2508.00031Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;systems_efficiency5agent-memory
492508.012872025-08-02baseline-2025H2-Jan2026Exploitation Is All You Need... for Explorationhttps://arxiv.org/abs/2508.01287Falseperipheralsystems_costmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis4agent-memory
502508.014152025-08-02baseline-2025H2-Jan2026RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systemshttps://arxiv.org/abs/2508.01415Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;execution_state;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;execution_multimodal6agent-memory
512508.033412025-08-05baseline-2025H2-Jan2026What Deserves Memory: Adaptive Memory Distillation for LLM Agentshttps://arxiv.org/abs/2508.03341Truesupportingexperience_learningmodelupdate_forgetting;experience_skill_learning;systems_efficiencyexperience_skill_policy3episodic-memory
522508.050022025-08-07baseline-2025H2-Jan2026AgenticData: An Agentic Data Analytics System for Heterogeneous Datahttps://arxiv.org/abs/2508.05002Falsesupportingexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multi_agent_shared5agent-memory
532508.070102025-08-09baseline-2025H2-Jan2026Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TVhttps://arxiv.org/abs/2508.07010Truesupportingexecution_statemodelrepresentation_organization;update_forgetting;multi_agent_shared;multimodal_embodied_guipersonal_shared4episodic-memory
542508.089972025-08-12baseline-2025H2-Jan2026Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memoryhttps://arxiv.org/abs/2508.08997Truecoreupdate_forgettingmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencyretrieval_representation;personal_shared3agent-memory
552508.094862025-08-13baseline-2025H2-Jan2026Video-EM: Event-Centric Episodic Memory for Long-Form Video Understandinghttps://arxiv.org/abs/2508.09486Truesupportingexperience_learningmodelretrieval_access;experience_skill_learning;multimodal_embodied_guiexecution_multimodal0agent-memory;episodic-memory
562508.126302025-08-18baseline-2025H2-Jan2026Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Contexthttps://arxiv.org/abs/2508.12630Truesupportingexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal7agent-memory
572508.132502025-08-18baseline-2025H2-Jan2026Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Informationhttps://arxiv.org/abs/2508.13250Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosispersonal_shared5agent-memory
582508.152942025-08-21baseline-2025H2-Jan2026A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agentshttps://arxiv.org/abs/2508.15294Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis3agent-memory
592508.161532025-08-22baseline-2025H2-Jan2026Memento: Fine-tuning LLM Agents without Fine-tuning LLMshttps://arxiv.org/abs/2508.16153Falsecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency3episodic-memory
602508.190052025-08-26baseline-2025H2-Jan2026Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmarkhttps://arxiv.org/abs/2508.19005Falsesupportingexecution_statemodelrepresentation_organization;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy2agent-memory
612509.009972025-08-31baseline-2025H2-Jan2026Supporting Our AI Overlords: Redesigning Data Systems to be Agent-Firsthttps://arxiv.org/abs/2509.00997Falsesupportingexecution_statemodelretrieval_access;systems_efficiency0agent-memory
622509.119142025-09-15baseline-2025H2-Jan2026EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Modelshttps://arxiv.org/abs/2509.11914Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;multimodal_embodied_gui6agent-memory
632509.212242025-09-25baseline-2025H2-Jan2026What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patternshttps://arxiv.org/abs/2509.21224Falsecoreexecution_statemodelevaluation_diagnosis;multimodal_embodied_gui2long-term-memory
642509.252502025-09-27baseline-2025H2-Jan2026Memory Management and Contextual Consistency for Long-Running Low-Code Agentshttps://arxiv.org/abs/2509.25250Truecoreupdate_forgettingmodelupdate_forgetting;multimodal_embodied_gui;systems_efficiency5agent-memory
652509.247042025-09-29baseline-2025H2-Jan2026MemGen: Weaving Generative Latent Memory for Self-Evolving Agentshttps://arxiv.org/abs/2509.24704Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy2agent-memory
662510.023732025-09-29baseline-2025H2-Jan2026A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memoryhttps://arxiv.org/abs/2510.02373Truecoresecurity_privacymodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiency6agent-memory
672510.036122025-10-04baseline-2025H2-Jan2026Cross-Modal Content Optimization for Steering Web Agent Preferenceshttps://arxiv.org/abs/2510.03612Falsecoreupdate_forgettingmodelevaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiexecution_multimodal7agent-memory
682510.046182025-10-06baseline-2025H2-Jan2026Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelshttps://arxiv.org/abs/2510.04618Falsecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy8agent-memory
692510.048512025-10-06baseline-2025H2-Jan2026LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automationhttps://arxiv.org/abs/2510.04851Truecoreexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_sharedexperience_skill_policy;personal_shared2agent-memory
702510.055202025-10-07baseline-2025H2-Jan2026CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehensionhttps://arxiv.org/abs/2510.05520Truecoreaccessmodelretrieval_access;representation_organization;systems_efficiency2agent-memory
712510.080812025-10-09baseline-2025H2-Jan2026AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessmenthttps://arxiv.org/abs/2510.08081Falsecoreexperience_learningmodelretrieval_access;experience_skill_learning3long-term-memory
722510.097202025-10-10baseline-2025H2-Jan2026Preference-Aware Memory Update for Long-Term LLM Agentshttps://arxiv.org/abs/2510.09720Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;systems_efficiencyupdate_forgetting5long-term-memory
732510.159662025-10-12baseline-2025H2-Jan2026PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agencyhttps://arxiv.org/abs/2510.15966Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis4agent-memory
742510.111442025-10-13baseline-2025H2-Jan2026$How^{2}$: How to learn from procedural How-to questionshttps://arxiv.org/abs/2510.11144Falsecoreexperience_learningmodelexecution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy2agent-memory
752510.138962025-10-14baseline-2025H2-Jan2026GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agentshttps://arxiv.org/abs/2510.13896Falsecoreshared_memorymodelrepresentation_organization;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui5long-term-memory
762510.156202025-10-17baseline-2025H2-Jan2026On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwardinghttps://arxiv.org/abs/2510.15620Falsecoreexecution_statemodelretrieval_access;evaluation_diagnosis;systems_efficiencysystems_efficiency6agent-memory
772510.185152025-10-21baseline-2025H2-Jan2026Socialized Learning and Emergent Behaviors in Multi-Agent Systems based on Multimodal Large Language Modelshttps://arxiv.org/abs/2510.18515Falsecoreshared_memorymodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;execution_multimodal;personal_shared5episodic-memory
782510.197472025-10-22baseline-2025H2-Jan2026Review of Tools for Zero-Code LLM Based Application Developmenthttps://arxiv.org/abs/2510.19747Falsecoreshared_memorymodelmultimodal_embodied_gui1agent-memory
792510.198972025-10-22baseline-2025H2-Jan2026Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptationhttps://arxiv.org/abs/2510.19897Truecorerepresentationmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy4episodic-memory
802510.237302025-10-27baseline-2025H2-Jan2026Evaluating Long-Term Memory for Long-Context Question Answeringhttps://arxiv.org/abs/2510.23730Truecorerepresentationmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis2agent-memory;episodic-memory
812510.254232025-10-29baseline-2025H2-Jan2026What Challenges Do Developers Face in AI Agent Systems? An Empirical Study on Stack Overflow & GitHub Issueshttps://arxiv.org/abs/2510.25423Falsecorerepresentationmodelretrieval_access;execution_state;evaluation_diagnosisbenchmark_diagnosis2agent-memory
822510.265362025-10-30baseline-2025H2-Jan2026RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaborationhttps://arxiv.org/abs/2510.26536Truecorerepresentationmodelretrieval_access;representation_organization;execution_state;multi_agent_shared;multimodal_embodied_guiexecution_multimodal;systems_efficiency4agent-memory
832510.274182025-10-31baseline-2025H2-Jan2026Dynamic Affective Memory Management for Personalized LLM Agentshttps://arxiv.org/abs/2510.27418Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosispersonal_shared3long-term-memory
842511.014482025-11-03baseline-2025H2-Jan2026LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoninghttps://arxiv.org/abs/2511.01448Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencysystems_efficiency6agent-memory;long-term-memory
852511.024242025-11-04baseline-2025H2-Jan2026ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planninghttps://arxiv.org/abs/2511.02424Falsecorerepresentationmodelretrieval_access;representation_organization;execution_state;multimodal_embodied_guiretrieval_representation;execution_multimodal9episodic-memory
862511.034752025-11-05baseline-2025H2-Jan2026ContextPilot: Fast Long-Context Inference via Context Reusehttps://arxiv.org/abs/2511.03475Falsecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;multi_agent_shared;systems_efficiency5agent-memory
872511.061792025-11-09baseline-2025H2-Jan2026MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaceshttps://arxiv.org/abs/2511.06179Truecoreexperience_learningmodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiencyretrieval_representation;experience_skill_policy0agent-memory
882511.075872025-11-10baseline-2025H2-Jan2026Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaceshttps://arxiv.org/abs/2511.07587Truecorerepresentationmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencyretrieval_representation6episodic-memory
892511.083012025-11-11baseline-2025H2-Jan2026Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learninghttps://arxiv.org/abs/2511.08301Falsecoreexperience_learningmodelexperience_skill_learning;evaluation_diagnosis;multi_agent_sharedexperience_skill_policy5agent-memory
902511.120272025-11-15baseline-2025H2-Jan2026GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memoryhttps://arxiv.org/abs/2511.12027Truecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal6episodic-memory
912511.129972025-11-17baseline-2025H2-Jan2026WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancehttps://arxiv.org/abs/2511.12997Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;execution_multimodal4episodic-memory
922511.161082025-11-20baseline-2025H2-Jan2026SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agenthttps://arxiv.org/abs/2511.16108Falsecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;systems_efficiency6agent-memory
932511.177752025-11-21baseline-2025H2-Jan2026Episodic Memory in Agentic Frameworks: Suggesting Next Taskshttps://arxiv.org/abs/2511.17775Truecoreupdate_forgettingmodelretrieval_access;multimodal_embodied_gui0episodic-memory
942511.217302025-11-21baseline-2025H2-Jan2026A Benchmark for Procedural Memory Retrieval in Language Agentshttps://arxiv.org/abs/2511.21730Truecoreaccessmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;retrieval_representation;experience_skill_policy5procedural-memory
952511.181122025-11-22baseline-2025H2-Jan2026EchoVLA: Synergistic Declarative Memory for VLA-Driven Mobile Manipulationhttps://arxiv.org/abs/2511.18112Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui4episodic-memory
962511.184232025-11-23baseline-2025H2-Jan2026General Agentic Memory Via Deep Researchhttps://arxiv.org/abs/2511.18423Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;multimodal_embodied_guiretrieval_representation3agent-memory
972511.191922025-11-24baseline-2025H2-Jan2026AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphoneshttps://arxiv.org/abs/2511.19192Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencysystems_efficiency4agent-memory
982511.202972025-11-25baseline-2025H2-Jan2026Improving Language Agents through BREWhttps://arxiv.org/abs/2511.20297Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;systems_efficiency2agent-memory
992511.208572025-11-25baseline-2025H2-Jan2026Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memoryhttps://arxiv.org/abs/2511.20857Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;experience_skill_policy5memory-evaluation
1002512.007422025-11-30baseline-2025H2-Jan2026On the Regulatory Potential of User Interfaces for AI Agent Governancehttps://arxiv.org/abs/2512.00742Falsecoreaccessmodelrepresentation_organization;security_privacy_trustsecurity_governance0agent-memory
1012512.022272025-12-01baseline-2025H2-Jan2026Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Tradinghttps://arxiv.org/abs/2512.02227Falsecoreaccessmodelrepresentation_organization1agent-memory
1022512.022282025-12-01baseline-2025H2-Jan2026STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Callshttps://arxiv.org/abs/2512.02228Falsecoreaccessmodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency4long-term-memory
1032512.024252025-12-02baseline-2025H2-Jan2026WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoninghttps://arxiv.org/abs/2512.02425Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal8agent-memory;episodic-memory
1042512.024582025-12-02baseline-2025H2-Jan2026Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Explorationhttps://arxiv.org/abs/2512.02458Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal3agent-memory
1052512.036272025-12-03baseline-2025H2-Jan2026MemVerse: Multimodal Memory for Lifelong Learning Agentshttps://arxiv.org/abs/2512.03627Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;execution_multimodal4agent-memory
1062512.046682025-12-04baseline-2025H2-Jan2026Topology Matters: Measuring Memory Leakage in Multi-Agent LLMshttps://arxiv.org/abs/2512.04668Truecoreexecution_statemodelrepresentation_organization;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_guisecurity_governance;personal_shared4agent-memory
1072512.066882025-12-07baseline-2025H2-Jan2026PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memoryhttps://arxiv.org/abs/2512.06688Truecoreapplicationmodelexperience_skill_learning;systems_efficiencyexperience_skill_policy;personal_shared6agent-memory
1082512.094582025-12-10baseline-2025H2-Jan2026Architectures for Building Agentic AIhttps://arxiv.org/abs/2512.09458Falsecoreexecution_statemodelexecution_state;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiency1agent-memory
1092512.101662025-12-10baseline-2025H2-Jan2026Emergent Collective Memory in Decentralized Multi-Agent AI Systemshttps://arxiv.org/abs/2512.10166Truecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;multi_agent_sharedpersonal_shared7agent-memory
1102512.106962025-12-11baseline-2025H2-Jan2026Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutionhttps://arxiv.org/abs/2512.10696Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiencyexperience_skill_policy7agent-memory;procedural-memory
1112512.113032025-12-12baseline-2025H2-Jan2026Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecturehttps://arxiv.org/abs/2512.11303Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;systems_efficiencyexperience_skill_policy8agent-memory;episodic-memory
1122512.126862025-12-14baseline-2025H2-Jan2026Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AIhttps://arxiv.org/abs/2512.12686Truecoreaccessmodelrepresentation_organization;experience_skill_learning;systems_efficiencysystems_efficiency;personal_shared0agent-memory
1132512.128182025-12-14baseline-2025H2-Jan2026Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflectshttps://arxiv.org/abs/2512.12818Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiretrieval_representation7agent-memory;memory-evaluation
1142512.128562025-12-14baseline-2025H2-Jan2026Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agentshttps://arxiv.org/abs/2512.12856Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;update_forgetting;security_governance2agent-memory
1152512.129672025-12-15baseline-2025H2-Jan2026QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Managementhttps://arxiv.org/abs/2512.12967Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;systems_efficiency7agent-memory
1162512.135642025-12-15baseline-2025H2-Jan2026Memory in the Age of AI Agentshttps://arxiv.org/abs/2512.13564Truecoreaccessmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiency3agent-memory;memory-evaluation
1172512.163012025-12-18baseline-2025H2-Jan2026Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillshttps://arxiv.org/abs/2512.16301Truecoreexperience_learningmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;experience_skill_policy4long-term-memory
1182512.169622025-12-18baseline-2025H2-Jan2026MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrievalhttps://arxiv.org/abs/2512.16962Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;security_privacy_trustretrieval_representation;experience_skill_policy;security_governance3agent-memory;long-term-memory
1192512.183372025-12-20baseline-2025H2-Jan2026Towards Efficient Agents: A Co-Design of Inference Architecture and Systemhttps://arxiv.org/abs/2512.18337Falsecoreexecution_statemodelrepresentation_organization;execution_state;evaluation_diagnosis;systems_efficiencysystems_efficiency4agent-memory
1202512.185712025-12-21baseline-2025H2-Jan2026ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learninghttps://arxiv.org/abs/2512.18571Falsecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyretrieval_representation;experience_skill_policy;execution_multimodal;systems_efficiency6episodic-memory
1212512.187462025-12-21baseline-2025H2-Jan2026MemEvolve: Meta-Evolution of Agent Memory Systemshttps://arxiv.org/abs/2512.18746Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosisexperience_skill_policy2agent-memory
1222512.189502025-12-22baseline-2025H2-Jan2026Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinementhttps://arxiv.org/abs/2512.18950Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;systems_efficiencyretrieval_representation;experience_skill_policy5procedural-memory
1232512.195372025-12-22baseline-2025H2-Jan2026Event Extraction in Large Language Modelhttps://arxiv.org/abs/2512.19537Falsecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui3agent-memory
1242512.201112025-12-23baseline-2025H2-Jan2026ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interactionhttps://arxiv.org/abs/2512.20111Falsecoreupdate_forgettingmodelupdate_forgetting;execution_state;experience_skill_learning;systems_efficiencyexperience_skill_policy;systems_efficiency7agent-memory
1252512.215672025-12-25baseline-2025H2-Jan2026Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Managementhttps://arxiv.org/abs/2512.21567Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiency3agent-memory
1262512.227162025-12-27baseline-2025H2-Jan2026Memento 2: Learning by Stateful Reflective Memoryhttps://arxiv.org/abs/2512.22716Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy2episodic-memory
1272512.233432025-12-29baseline-2025H2-Jan2026AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentshttps://arxiv.org/abs/2512.23343Truecorerepresentationmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiency2agent-memory
1282601.018852026-01-05baseline-2025H2-Jan2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentshttps://arxiv.org/abs/2601.01885Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy5agent-memory;long-term-memory
1292601.025772026-01-05baseline-2025H2-Jan2026Orchestral AI: A Framework for Agent Orchestrationhttps://arxiv.org/abs/2601.02577Falsecorerepresentationmodelrepresentation_organization;systems_efficiency0agent-memory
1302601.027322026-01-06baseline-2025H2-Jan2026Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microserviceshttps://arxiv.org/abs/2601.02732Truecoreupdate_forgettingmodelmulti_agent_shared;systems_efficiency5agent-memory
1312601.027442026-01-06baseline-2025H2-Jan2026SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activationhttps://arxiv.org/abs/2601.02744Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis6agent-memory
1322601.032362026-01-06baseline-2025H2-Jan2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentshttps://arxiv.org/abs/2601.03236Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;multimodal_embodied_guiretrieval_representation4agent-memory
1332601.035432026-01-07baseline-2025H2-Jan2026EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memoryhttps://arxiv.org/abs/2601.03543Truecorerepresentationmodelevaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis6agent-memory
1342601.037852026-01-07baseline-2025H2-Jan2026Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agentshttps://arxiv.org/abs/2601.03785Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting4agent-memory
1352601.041702026-01-07baseline-2025H2-Jan2026Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactionshttps://arxiv.org/abs/2601.04170Falsesupportingexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multi_agent_shared;systems_efficiencypersonal_shared1episodic-memory
1362601.055042026-01-09baseline-2025H2-Jan2026Memory Poisoning Attack and Defense on Memory Based LLM-Agentshttps://arxiv.org/abs/2601.05504Truesupportingsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trustsecurity_governance6long-term-memory
1372601.062822026-01-09baseline-2025H2-Jan2026Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoninghttps://arxiv.org/abs/2601.06282Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiency8agent-memory
1382601.063772026-01-10baseline-2025H2-Jan2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentshttps://arxiv.org/abs/2601.06377Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyretrieval_representation;execution_multimodal6episodic-memory
1392601.064112026-01-10baseline-2025H2-Jan2026Structured Episodic Event Memoryhttps://arxiv.org/abs/2601.06411Truecoreexperience_learningmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trustretrieval_representation6episodic-memory
1402601.107442026-01-11baseline-2025H2-Jan2026Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Explorationhttps://arxiv.org/abs/2601.10744Truesupportingexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;experience_skill_policy;execution_multimodal4agent-memory;episodic-memory
1412601.074702026-01-12baseline-2025H2-Jan2026Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memoryhttps://arxiv.org/abs/2601.07470Truecoreexperience_learningmodelrepresentation_organization;execution_state;experience_skill_learningretrieval_representation;experience_skill_policy4agent-memory
1422601.077792026-01-12baseline-2025H2-Jan2026OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agenthttps://arxiv.org/abs/2601.07779Falsesupportingexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui6agent-memory
1432601.081602026-01-13baseline-2025H2-Jan2026SwiftMem: Fast Agentic Memory via Query-aware Indexinghttps://arxiv.org/abs/2601.08160Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation5agent-memory
1442601.083232026-01-13baseline-2025H2-Jan2026AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operationhttps://arxiv.org/abs/2601.08323Truecoreexperience_learningmodelrepresentation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisexperience_skill_policy4agent-memory
1452601.091132026-01-14baseline-2025H2-Jan2026The AI Hippocampus: How Far are We From Human Memory?https://arxiv.org/abs/2601.09113Truesupportingexperience_learningmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis2agent-memory
1462601.096362026-01-14baseline-2025H2-Jan2026PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Recordshttps://arxiv.org/abs/2601.09636Falsecoreexecution_statemodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_guiretrieval_representation;execution_multimodal;personal_shared5agent-memory
1472602.060512026-01-14baseline-2025H2-Jan2026CAST: Character-and-Scene Episodic Memory for Agentshttps://arxiv.org/abs/2602.06051Truecorerepresentationmodelretrieval_access;representation_organization;experience_skill_learning6agent-memory;episodic-memory
1482602.060522026-01-14baseline-2025H2-Jan2026Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Surveyhttps://arxiv.org/abs/2602.06052Truecoreaccessmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis2agent-memory
1492601.107022026-01-15baseline-2025H2-Jan2026Grounding Agent Memory in Contextual Intenthttps://arxiv.org/abs/2601.10702Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis6agent-memory
1502601.118542026-01-17baseline-2025H2-Jan2026ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systemshttps://arxiv.org/abs/2601.11854Falsecorerepresentationmodelexecution_state;evaluation_diagnosisbenchmark_diagnosis4agent-memory
1512601.127712026-01-19baseline-2025H2-Jan2026Who Does This Name Remind You of ? Nationality Prediction via Large Language Model Associative Memoryhttps://arxiv.org/abs/2601.12771Truecoreupdate_forgettingmodelretrieval_access;multi_agent_shared;multimodal_embodied_gui5agent-memory
1522601.141922026-01-20baseline-2025H2-Jan2026Toward Efficient Agents: Memory, Tool learning, and Planninghttps://arxiv.org/abs/2601.14192Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy;systems_efficiency3agent-memory
1532601.147352026-01-21baseline-2025H2-Jan2026Optimizing FaaS Platforms for MCP-enabled Agentic Workflowshttps://arxiv.org/abs/2601.14735Falsecoreexecution_statemodelretrieval_access;evaluation_diagnosis;multi_agent_shared;systems_efficiency4agent-memory
1542601.166902026-01-23baseline-2025H2-Jan2026EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agentshttps://arxiv.org/abs/2601.16690Truecoreexperience_learningmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guibenchmark_diagnosis6agent-memory
1552601.168722026-01-23baseline-2025H2-Jan2026From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modelinghttps://arxiv.org/abs/2601.16872Truecoreupdate_forgettingmodelrepresentation_organization;update_forgettingretrieval_representation;experience_skill_policy4agent-memory
1562601.178872026-01-25baseline-2025H2-Jan2026When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agentshttps://arxiv.org/abs/2601.17887Falsecoreexecution_statemodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;security_privacy_trustsecurity_governance;personal_shared6long-term-memory
1572601.186422026-01-26baseline-2025H2-Jan2026FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memoryhttps://arxiv.org/abs/2601.18642Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyupdate_forgetting;systems_efficiency3agent-memory
1582601.203522026-01-28baseline-2025H2-Jan2026AMA: Adaptive Memory via Multi-Agent Collaborationhttps://arxiv.org/abs/2601.20352Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multi_agent_shared;systems_efficiencyexperience_skill_policy;personal_shared7agent-memory;long-term-memory
1592601.204652026-01-28baseline-2025H2-Jan2026BMAM: Brain-inspired Multi-Agent Memory Frameworkhttps://arxiv.org/abs/2601.20465Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multi_agent_shared;systems_efficiencypersonal_shared4agent-memory
1602601.214682026-01-29baseline-2025H2-Jan2026MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoninghttps://arxiv.org/abs/2601.21468Truecoreupdate_forgettingmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;systems_efficiency4agent-memory
1612601.217142026-01-29baseline-2025H2-Jan2026E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memoryhttps://arxiv.org/abs/2601.21714Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencypersonal_shared2agent-memory
1622601.218412026-01-29baseline-2025H2-Jan2026Embodied Task Planning via Graph-Informed Action Generation with Large Language Modelshttps://arxiv.org/abs/2601.21841Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal7agent-memory
1632601.229642026-01-30baseline-2025H2-Jan2026EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learninghttps://arxiv.org/abs/2601.22964Falsecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;experience_skill_policy5agent-memory
1642601.229742026-01-30baseline-2025H2-Jan2026MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocationhttps://arxiv.org/abs/2601.22974Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;execution_state;multi_agent_shared;multimodal_embodied_guiretrieval_representation;personal_shared4episodic-memory
1652601.230142026-01-30baseline-2025H2-Jan2026Mem-T: Densifying Rewards for Long-Horizon Memory Agentshttps://arxiv.org/abs/2601.23014Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexecution_multimodal3agent-memory
1662602.003522026-01-30baseline-2025H2-Jan2026DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoninghttps://arxiv.org/abs/2602.00352Falsecoreaccessmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;retrieval_representation4agent-memory
1672602.003642026-01-30baseline-2025H2-Jan2026"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrievalhttps://arxiv.org/abs/2602.00364Falsecoreaccessmodelretrieval_access;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;security_governance2agent-memory
1682602.006752026-01-31baseline-2025H2-Jan2026Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interactionhttps://arxiv.org/abs/2602.00675Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal3agent-memory
1692602.018692026-02-02transition-2026-Feb-MarSkill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentshttps://arxiv.org/abs/2602.01869Falsecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy3procedural-memory
1702602.020072026-02-02transition-2026-Feb-MarBeyond RAG for Agent Memory: Retrieval by Decoupling and Aggregationhttps://arxiv.org/abs/2602.02007Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;multimodal_embodied_gui;systems_efficiencyretrieval_representation2agent-memory
1712602.021642026-02-02transition-2026-Feb-MarCo-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agentshttps://arxiv.org/abs/2602.02164Falsesupportingsecurity_privacymodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_sharedsecurity_governance7long-term-memory
1722602.023692026-02-02transition-2026-Feb-MarLive-Evo: Online Evolution of Agentic Memory from Continuous Feedbackhttps://arxiv.org/abs/2602.02369Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui5agent-memory
1732602.024742026-02-02transition-2026-Feb-MarMemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentshttps://arxiv.org/abs/2602.02474Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy5agent-memory
1742602.030362026-02-03transition-2026-Feb-MarLatentMem: Customizing Latent Memory for Multi-Agent Systemshttps://arxiv.org/abs/2602.03036Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;systems_efficiencypersonal_shared5agent-memory
1752602.032242026-02-03transition-2026-Feb-MarTAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarkinghttps://arxiv.org/abs/2602.03224Truecoresecurity_privacymodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_guibenchmark_diagnosis;security_governance2agent-memory
1762602.033152026-02-03transition-2026-Feb-MarMemora: A Harmonic Memory Representation Balancing Abstraction and Specificityhttps://arxiv.org/abs/2602.03315Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation2agent-memory
1772602.044822026-02-04transition-2026-Feb-MarProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Datahttps://arxiv.org/abs/2602.04482Falsesupportingapplicationmodelrepresentation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis7long-term-memory
1782602.046402026-02-04transition-2026-Feb-MarTowards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agentshttps://arxiv.org/abs/2602.04640Falsecoreupdate_forgettingmodelrepresentation_organization;execution_stateretrieval_representation0agent-memory
1792603.000262026-02-04transition-2026-Feb-MarActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agentshttps://arxiv.org/abs/2603.00026Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosisretrieval_representation6memory-evaluation
1802602.056652026-02-05transition-2026-Feb-MarGraph-based Agent Memory: Taxonomy, Techniques, and Applicationshttps://arxiv.org/abs/2602.05665Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;retrieval_representation5agent-memory
1812602.060252026-02-05transition-2026-Feb-MarLearning Query-Aware Budget-Tier Routing for Runtime Agent Memoryhttps://arxiv.org/abs/2602.06025Truesupportingapplicationmodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiencyexperience_skill_policy;systems_efficiency2agent-memory
1822602.176922026-02-06transition-2026-Feb-MarAgentic Unlearning: When LLM Agent Meets Machine Unlearninghttps://arxiv.org/abs/2602.17692Falsecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;security_governance2long-term-memory
1832603.032962026-02-06transition-2026-Feb-MarPlugMem: A Task-Agnostic Plugin Memory Module for LLM Agentshttps://arxiv.org/abs/2603.03296Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency5episodic-memory;long-term-memory
1842602.073982026-02-07transition-2026-Feb-MarAgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Managementhttps://arxiv.org/abs/2602.07398Truecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;security_privacy_trustretrieval_representation6agent-memory
1852602.076242026-02-07transition-2026-Feb-MarM2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactionshttps://arxiv.org/abs/2602.07624Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;personal_shared6agent-memory
1862602.077552026-02-08transition-2026-Feb-MarLearning to Continually Learn via Meta-learning Agentic Memory Designshttps://arxiv.org/abs/2602.07755Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy3agent-memory
1872602.078852026-02-08transition-2026-Feb-MarMemFly: On-the-Fly Memory Optimization via Information Bottleneckhttps://arxiv.org/abs/2602.07885Truecoreupdate_forgettingmodelretrieval_access;representation_organization;systems_efficiency4long-term-memory
1882602.083692026-02-09transition-2026-Feb-MarMemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrievalhttps://arxiv.org/abs/2602.08369Truecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosis;systems_efficiencyretrieval_representation;experience_skill_policy6agent-memory
1892602.093192026-02-10transition-2026-Feb-MarBenchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generationhttps://arxiv.org/abs/2602.09319Falsecoreaccessmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis;retrieval_representation;security_governance;systems_efficiency2agent-memory
1902602.097122026-02-10transition-2026-Feb-MarTraceMem: Weaving Narrative Memory Schemata from User Conversational Traceshttps://arxiv.org/abs/2602.09712Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis6episodic-memory
1912602.107152026-02-11transition-2026-Feb-MarLocomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agentshttps://arxiv.org/abs/2602.10715Truecoreexecution_statemodelretrieval_access;evaluation_diagnosisbenchmark_diagnosis4memory-evaluation
1922602.112432026-02-11transition-2026-Feb-MarEvaluating Memory Structure in LLM Agentshttps://arxiv.org/abs/2602.11243Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;retrieval_representation3agent-memory;long-term-memory;memory-evaluation
1932602.135302026-02-13transition-2026-Feb-MarREMem: Reasoning with Episodic Memory in Language Agenthttps://arxiv.org/abs/2602.13530Truecorerepresentationmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis6memory-evaluation
1942602.184932026-02-13transition-2026-Feb-MarLearning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoninghttps://arxiv.org/abs/2602.18493Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisexperience_skill_policy4agent-memory
1952602.135942026-02-14transition-2026-Feb-MarHippocampus: An Efficient and Scalable Memory Module for Agentic AIhttps://arxiv.org/abs/2602.13594Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;systems_efficiencysystems_efficiency2agent-memory
1962602.139332026-02-15transition-2026-Feb-MarHyMem: Hybrid Memory Architecture with Dynamic Retrieval Schedulinghttps://arxiv.org/abs/2602.13933Truecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;systems_efficiencyretrieval_representation6long-term-memory
1972602.140382026-02-15transition-2026-Feb-MarChoosing How to Remember: Adaptive Memory Structures for LLM Agentshttps://arxiv.org/abs/2602.14038Truecoreexecution_statemodelrepresentation_organization;execution_state;evaluation_diagnosisretrieval_representation;experience_skill_policy4agent-memory
1982602.152742026-02-17transition-2026-Feb-MarWhen Remembering and Planning are Worth it: Navigating under Changehttps://arxiv.org/abs/2602.15274Truecoreexecution_statemodelretrieval_access;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiency0agent-memory
1992602.155132026-02-17transition-2026-Feb-MarHIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answeringhttps://arxiv.org/abs/2602.15513Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal4episodic-memory
2002602.156542026-02-17transition-2026-Feb-MarZombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injectionshttps://arxiv.org/abs/2602.15654Falsecoreexecution_statemodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiencyexperience_skill_policy3long-term-memory
2012603.022402026-02-17transition-2026-Feb-MarSuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoninghttps://arxiv.org/abs/2603.02240Truecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencysecurity_governance;systems_efficiency;personal_shared5agent-memory
2022603.044282026-02-17transition-2026-Feb-MarAgent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Deviceshttps://arxiv.org/abs/2603.04428Truecoreexecution_statemodelevaluation_diagnosis;multi_agent_shared;systems_efficiencysystems_efficiency;personal_shared5agent-memory
2032602.163132026-02-18transition-2026-Feb-MarMemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Taskshttps://arxiv.org/abs/2602.16313Truecoreexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis3agent-memory;memory-evaluation
2042602.164932026-02-18transition-2026-Feb-MarMMA: Multimodal Memory Agenthttps://arxiv.org/abs/2602.16493Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal8agent-memory
2052602.193202026-02-22transition-2026-Feb-MarAnatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationshttps://arxiv.org/abs/2602.19320Truecoreexecution_statemodelrepresentation_organization;execution_state;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis4agent-memory
2062603.044432026-02-22transition-2026-Feb-MarAMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systemshttps://arxiv.org/abs/2603.04443Truecoreexecution_statemodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencyupdate_forgetting;systems_efficiency7agent-memory;long-term-memory
2072602.213942026-02-24transition-2026-Feb-MarMemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detectionhttps://arxiv.org/abs/2602.21394Truecoreexecution_statemodelretrieval_access;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui8episodic-memory
2082602.214772026-02-25transition-2026-Feb-MarPancake: Hierarchical Memory System for Multi-Agent LLM Servinghttps://arxiv.org/abs/2602.21477Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;multi_agent_shared;systems_efficiencyretrieval_representation;systems_efficiency;personal_shared6agent-memory
2092602.224062026-02-25transition-2026-Feb-MarTowards Autonomous Memory Agentshttps://arxiv.org/abs/2602.22406Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;systems_efficiency6agent-memory
2102602.227692026-02-26transition-2026-Feb-MarAMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationshttps://arxiv.org/abs/2602.22769Truecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosisbenchmark_diagnosis;execution_multimodal8agent-memory;memory-evaluation
2112602.237202026-02-27transition-2026-Feb-MarThe Auton Agentic AI Frameworkhttps://arxiv.org/abs/2602.23720Falsecoreexecution_statemodelrepresentation_organization;update_forgetting;experience_skill_learning;security_privacy_trust;systems_efficiency0episodic-memory
2122602.239372026-02-27transition-2026-Feb-MarEnhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videoshttps://arxiv.org/abs/2602.23937Falsecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal;systems_efficiency4episodic-memory
2132603.011602026-03-01transition-2026-Feb-MarSemantic XPath: Structured Agentic Memory Access for Conversational AIhttps://arxiv.org/abs/2603.01160Truecoreaccessmodelretrieval_access;representation_organization;update_forgetting;multimodal_embodied_gui;systems_efficiencyretrieval_representation4agent-memory
2142603.019662026-03-02transition-2026-Feb-MarAMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversationshttps://arxiv.org/abs/2603.01966Truecoreupdate_forgettingmodelrepresentation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal2agent-memory;memory-evaluation
2152603.022062026-03-02transition-2026-Feb-MarVoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectureshttps://arxiv.org/abs/2603.02206Falsecoreaccessmodelretrieval_access;representation_organization;systems_efficiencyretrieval_representation;systems_efficiency1agent-memory
2162603.024732026-03-02transition-2026-Feb-MarDiagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memoryhttps://arxiv.org/abs/2603.02473Truecoreaccessmodelretrieval_access;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;retrieval_representation6agent-memory
2172603.030242026-03-03transition-2026-Feb-MarMA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLNhttps://arxiv.org/abs/2603.03024Falsecoreupdate_forgettingmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal;personal_shared4agent-memory
2182603.031482026-03-03transition-2026-Feb-MarFrom Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?https://arxiv.org/abs/2603.03148Falsecoreexecution_statemodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal4episodic-memory
2192603.156422026-03-03transition-2026-Feb-MarCraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systemshttps://arxiv.org/abs/2603.15642Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis5agent-memory
2202603.045492026-03-04transition-2026-Feb-MarAdaptive Memory Admission Control for LLM Agentshttps://arxiv.org/abs/2603.04549Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyexperience_skill_policy7long-term-memory
2212603.047402026-03-05transition-2026-Feb-MarMemory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizenshttps://arxiv.org/abs/2603.04740Truecoreexecution_statemodelretrieval_access;representation_organization;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyretrieval_representation0agent-memory
2222603.235162026-03-06transition-2026-Feb-MarMSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokenshttps://arxiv.org/abs/2603.23516Truecoreupdate_forgettingmodelevaluation_diagnosis;systems_efficiencysystems_efficiency5agent-memory
2232603.087552026-03-07transition-2026-Feb-MarTurn: A Language for Agentic Computationhttps://arxiv.org/abs/2603.08755Falsecoreupdate_forgettingmodelevaluation_diagnosis3agent-memory
2242603.073922026-03-08transition-2026-Feb-MarCan Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streamshttps://arxiv.org/abs/2603.07392Falsecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy;systems_efficiency4agent-memory
2252603.076702026-03-08transition-2026-Feb-MarMemory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiershttps://arxiv.org/abs/2603.07670Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis2agent-memory
2262603.077842026-03-08transition-2026-Feb-MarProgAgent:A Continual RL Agent with Progress-Aware Rewardshttps://arxiv.org/abs/2603.07784Falsecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy4agent-memory
2272603.100622026-03-09transition-2026-Feb-MarMulti-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Aheadhttps://arxiv.org/abs/2603.10062Truecoreexecution_statemodelrepresentation_organization;multi_agent_shared;multimodal_embodied_guipersonal_shared0agent-memory
2282604.000092026-03-09transition-2026-Feb-MarEyla: Toward an Identity-Anchored LLM Architecture with Integrated Biological Priors -- Vision, Implementation Attempt, and Lessons from AI-Assisted Developmenthttps://arxiv.org/abs/2604.00009Falsecorerepresentationmodelretrieval_access;evaluation_diagnosis;security_privacy_trust5episodic-memory
2292603.117212026-03-12transition-2026-Feb-MarWhen OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflowshttps://arxiv.org/abs/2603.11721Falsecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency7long-term-memory
2302603.117682026-03-12transition-2026-Feb-MarGoverning Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkhttps://arxiv.org/abs/2603.11768Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;security_governance0agent-memory;long-term-memory
2312603.126312026-03-13transition-2026-Feb-MarJoint Optimization of Multi-agent Memory Systemhttps://arxiv.org/abs/2603.12631Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;multi_agent_shared;multimodal_embodied_guipersonal_shared5agent-memory
2322603.130172026-03-13transition-2026-Feb-MarStructured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservationhttps://arxiv.org/abs/2603.13017Truecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencyretrieval_representation;experience_skill_policy;systems_efficiency;personal_shared8agent-memory
2332603.136762026-03-14transition-2026-Feb-MarTheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranosticshttps://arxiv.org/abs/2603.13676Truecoreexecution_statemodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_sharedexperience_skill_policy;personal_shared7agent-memory
2342603.145882026-03-15transition-2026-Feb-MarSuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memoryhttps://arxiv.org/abs/2603.14588Truecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis6agent-memory
2352603.145972026-03-15transition-2026-Feb-MarD-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routinghttps://arxiv.org/abs/2603.14597Truecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiency7agent-memory;long-term-memory
2362603.152802026-03-16transition-2026-Feb-MarAdvancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memoryhttps://arxiv.org/abs/2603.15280Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal5agent-memory
2372603.154212026-03-16transition-2026-Feb-MarCLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agentshttps://arxiv.org/abs/2603.15421Truecoreaccessmodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiencyretrieval_representation;experience_skill_policy2agent-memory
2382603.167342026-03-17transition-2026-Feb-MarDifferential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosurehttps://arxiv.org/abs/2603.16734Falsecoreexecution_statemodelevaluation_diagnosis;security_privacy_trustpersonal_shared4long-term-memory
2392603.170432026-03-17transition-2026-Feb-MarOpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materialshttps://arxiv.org/abs/2603.17043Falsecoreexecution_statemodelretrieval_access;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis0long-term-memory
2402603.172442026-03-18transition-2026-Feb-MarGraph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectureshttps://arxiv.org/abs/2603.17244Truecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;update_forgetting6agent-memory;memory-evaluation
2412603.178312026-03-18transition-2026-Feb-MarRPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergyhttps://arxiv.org/abs/2603.17831Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal6episodic-memory
2422603.179482026-03-18transition-2026-Feb-MarVideoAtlas: Navigating Long-Form Video in Logarithmic Computehttps://arxiv.org/abs/2603.17948Falsecoreexperience_learningmodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal2agent-memory
2432603.199352026-03-20transition-2026-Feb-MarMemori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agentshttps://arxiv.org/abs/2603.19935Truecoreexperience_learningmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencysystems_efficiency6long-term-memory
2442604.141582026-03-23transition-2026-Feb-MarMemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarioshttps://arxiv.org/abs/2604.14158Truesupportingevaluationmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosisbenchmark_diagnosis3agent-memory
2452605.201892026-03-23transition-2026-Feb-MarSOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptationhttps://arxiv.org/abs/2605.20189Falsesupportingevaluationmodelupdate_forgetting;experience_skill_learning;systems_efficiencyexperience_skill_policy6episodic-memory
2462603.230642026-03-24transition-2026-Feb-MarMind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollutionhttps://arxiv.org/abs/2603.23064Trueperipheralsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trust3agent-memory
2472603.231602026-03-24transition-2026-Feb-MarUniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilitieshttps://arxiv.org/abs/2603.23160Falsesupportingevaluationmodelrepresentation_organization;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis6agent-memory
2482603.232312026-03-24transition-2026-Feb-MarPERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentshttps://arxiv.org/abs/2603.23231Truecoreexperience_learningmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;personal_shared5agent-memory
2492603.245642026-03-25transition-2026-Feb-MarInfrastructure for Valuable, Tradable, and Verifiable Agent Memoryhttps://arxiv.org/abs/2603.24564Truesupportingevaluationmodelrepresentation_organization;security_privacy_trust;systems_efficiencyretrieval_representation0agent-memory
2502603.250972026-03-26transition-2026-Feb-MarElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agentshttps://arxiv.org/abs/2603.25097Falsecoreevaluationmodelretrieval_access;representation_organization;update_forgetting;security_privacy_trust;systems_efficiencysecurity_governance;systems_efficiency0agent-memory
2512603.259732026-03-26transition-2026-Feb-MarMemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationhttps://arxiv.org/abs/2603.25973Truesupportingevaluationmodelevaluation_diagnosis;systems_efficiencybenchmark_diagnosis;personal_shared5memory-evaluation
2522604.197712026-03-27transition-2026-Feb-MarCognis: Context-Aware Memory for Conversational AI Agentshttps://arxiv.org/abs/2604.19771Truecoreexperience_learningmodelretrieval_access;evaluation_diagnosis;systems_efficiency4long-term-memory
2532603.280882026-03-30transition-2026-Feb-MarGEMS: Agent-Native Multimodal Generation with Memory and Skillshttps://arxiv.org/abs/2603.28088Truecoreexperience_learningmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_guiexperience_skill_policy;execution_multimodal4agent-memory
2542603.294932026-03-31transition-2026-Feb-MarMemFactory: Unified Inference & Training Framework for Agent Memoryhttps://arxiv.org/abs/2603.29493Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis6agent-memory
2552604.001312026-03-31transition-2026-Feb-MarOblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activationhttps://arxiv.org/abs/2604.00131Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyupdate_forgetting;experience_skill_policy2agent-memory
2562604.005562026-04-01recent-2026-Apr-JulHabitatAgent: An End-to-End Multi-Agent System for Housing Consultationhttps://arxiv.org/abs/2604.00556Falsecoreexperience_learningmodelretrieval_access;update_forgetting;evaluation_diagnosis;multi_agent_sharedpersonal_shared6agent-memory
2572604.010072026-04-01recent-2026-Apr-JulOmni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memoryhttps://arxiv.org/abs/2604.01007Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiretrieval_representation;execution_multimodal8agent-memory
2582604.015602026-04-02recent-2026-Apr-JulDeltaMem: Towards Agentic Memory Management via Reinforcement Learninghttps://arxiv.org/abs/2604.01560Truecoreupdate_forgettingmodelexperience_skill_learning;evaluation_diagnosis;multi_agent_sharedexperience_skill_policy4agent-memory;memory-evaluation
2592604.016582026-04-02recent-2026-Apr-JulCORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discoveryhttps://arxiv.org/abs/2604.01658Falsecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multi_agent_sharedpersonal_shared5long-term-memory
2602604.017072026-04-02recent-2026-Apr-JulMemory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkhttps://arxiv.org/abs/2604.01707Truecoreaccessmodelretrieval_access;execution_state;evaluation_diagnosis4agent-memory
2612604.025222026-04-02recent-2026-Apr-JulOpal: Private Memory for Personal AIhttps://arxiv.org/abs/2604.02522Truecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiency6agent-memory
2622604.026232026-04-03recent-2026-Apr-JulPoison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agentshttps://arxiv.org/abs/2604.02623Truecoreupdate_forgettingmodelretrieval_access;execution_state;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;security_governance4agent-memory
2632604.035882026-04-04recent-2026-Apr-JulRashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memoryhttps://arxiv.org/abs/2604.03588Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation0agent-memory
2642604.041572026-04-05recent-2026-Apr-JulReadable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agentshttps://arxiv.org/abs/2604.04157Falsecoreexecution_statemodel8long-term-memory
2652604.045032026-04-06recent-2026-Apr-JulMemory Intelligence Agenthttps://arxiv.org/abs/2604.04503Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency3agent-memory
2662604.045142026-04-06recent-2026-Apr-JulSuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systemshttps://arxiv.org/abs/2604.04514Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;update_forgetting4agent-memory
2672604.046602026-04-06recent-2026-Apr-JulSpringdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perceptionhttps://arxiv.org/abs/2604.04660Truesupportingexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_guisystems_efficiency6long-term-memory
2682604.048532026-04-06recent-2026-Apr-JulMemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agentshttps://arxiv.org/abs/2604.04853Truecoreexperience_learningmodelretrieval_access;execution_state;evaluation_diagnosis;systems_efficiencysystems_efficiency;personal_shared6long-term-memory
2692604.049012026-04-06recent-2026-Apr-JulFileGram: Grounding Agent Personalization in File-System Behavioral Traceshttps://arxiv.org/abs/2604.04901Falsesupportingexecution_statemodelretrieval_access;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guipersonal_shared2agent-memory
2702604.057192026-04-07recent-2026-Apr-JulHackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testinghttps://arxiv.org/abs/2604.05719Falsesupportingexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis5agent-memory
2712604.077982026-04-09recent-2026-Apr-JulLightweight LLM Agent Memory with Small Language Modelshttps://arxiv.org/abs/2604.07798Truecoreexperience_learningmodelretrieval_access;update_forgetting;execution_state;systems_efficiency2agent-memory;long-term-memory
2722604.078772026-04-09recent-2026-Apr-JulMemReader: From Passive to Active Extraction for Long-Term Agent Memoryhttps://arxiv.org/abs/2604.07877Truecoreexperience_learningmodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency5agent-memory
2732604.080642026-04-09recent-2026-Apr-JulImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Modelshttps://arxiv.org/abs/2604.08064Falsesupportingexecution_statemodelretrieval_access;experience_skill_learning;evaluation_diagnosisexperience_skill_policy8memory-evaluation;procedural-memory
2742604.087562026-04-09recent-2026-Apr-JulArtifacts as Memory Beyond the Agent Boundaryhttps://arxiv.org/abs/2604.08756Truesupportingexecution_statemodelexperience_skill_learning2agent-memory
2752604.090002026-04-10recent-2026-Apr-JulStreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understandinghttps://arxiv.org/abs/2604.09000Truecoreexperience_learningmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;systems_efficiency5agent-memory
2762604.093882026-04-10recent-2026-Apr-JulThe AI Codebase Maturity Model: From Assisted Coding to Fully Autonomous Systemshttps://arxiv.org/abs/2604.09388Falsecoreexperience_learningmodelrepresentation_organization;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;systems_efficiency3agent-memory
2772604.097472026-04-10recent-2026-Apr-JulADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Queryinghttps://arxiv.org/abs/2604.09747Truesupportingexecution_statemodelretrieval_access;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;security_governance6agent-memory
2782604.118112026-04-10recent-2026-Apr-JulM$^\star$: Every Task Deserves Its Own Memory Harnesshttps://arxiv.org/abs/2604.11811Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency5agent-memory
2792604.109812026-04-13recent-2026-Apr-JulATANT v1.1: Positioning Continuity Evaluation Against Memory, Long-Context, and Agentic-Memory Benchmarkshttps://arxiv.org/abs/2604.10981Truesupportingevaluationmodelevaluation_diagnosis;security_privacy_trustbenchmark_diagnosis5agent-memory;memory-evaluation
2802604.115442026-04-13recent-2026-Apr-JulTime is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memoryhttps://arxiv.org/abs/2604.11544Truecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_guiretrieval_representation;systems_efficiency4agent-memory
2812604.115632026-04-13recent-2026-Apr-JulSynthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMohttps://arxiv.org/abs/2604.11563Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiency8long-term-memory
2822604.120072026-04-13recent-2026-Apr-JulWhen to Forget: A Memory Governance Primitivehttps://arxiv.org/abs/2604.12007Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trustupdate_forgetting;security_governance6agent-memory
2832604.121792026-04-14recent-2026-Apr-JulAgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMshttps://arxiv.org/abs/2604.12179Truecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal2long-term-memory
2842604.122852026-04-14recent-2026-Apr-JulGAM: Hierarchical Graph-based Agentic Memory for LLM Agentshttps://arxiv.org/abs/2604.12285Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;multimodal_embodied_gui;systems_efficiencyretrieval_representation4agent-memory
2852604.129482026-04-14recent-2026-Apr-JulDrawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agentshttps://arxiv.org/abs/2604.12948Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation7long-term-memory
2862604.157742026-04-17recent-2026-Apr-JulMemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agentshttps://arxiv.org/abs/2604.15774Truesupportingevaluationmodelupdate_forgetting;execution_state;evaluation_diagnosis;security_privacy_trustbenchmark_diagnosis4long-term-memory
2872604.158772026-04-17recent-2026-Apr-JulExperience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentshttps://arxiv.org/abs/2604.15877Truesupportingevaluationmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy;systems_efficiency2agent-memory;episodic-memory
2882604.165482026-04-17recent-2026-Apr-JulA Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecyclehttps://arxiv.org/abs/2604.16548Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;security_privacy_trust;systems_efficiencybenchmark_diagnosis;update_forgetting;security_governance0long-term-memory
2892604.168392026-04-18recent-2026-Apr-JulHeLa-Mem: Hebbian Learning and Associative Memory for LLM Agentshttps://arxiv.org/abs/2604.16839Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;systems_efficiencyexperience_skill_policy5episodic-memory;long-term-memory
2902604.172732026-04-19recent-2026-Apr-JulThe Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forwardhttps://arxiv.org/abs/2604.17273Falsecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiency3agent-memory;memory-evaluation
2912604.174562026-04-19recent-2026-Apr-JulTrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Controlhttps://arxiv.org/abs/2604.17456Falsecoreexecution_statemodelrepresentation_organization;execution_state;experience_skill_learning3long-term-memory
2922604.176582026-04-19recent-2026-Apr-JulTowards Self-Improving Error Diagnosis in Multi-Agent Systemshttps://arxiv.org/abs/2604.17658Falsecoreexecution_statemodelupdate_forgetting;evaluation_diagnosis;multi_agent_sharedbenchmark_diagnosis;personal_shared6episodic-memory
2932604.195412026-04-21recent-2026-Apr-JulFOCAL: Filtered On-device Continuous Activity Logging for Efficient Personal Desktop Summarizationhttps://arxiv.org/abs/2604.19541Falsecoreexecution_statemodelretrieval_access;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiencysystems_efficiency6agent-memory
2942604.200062026-04-21recent-2026-Apr-JulFrom Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agentshttps://arxiv.org/abs/2604.20006Truecoreexecution_statemodelretrieval_access;update_forgetting;evaluation_diagnosisbenchmark_diagnosis;retrieval_representation;update_forgetting;personal_shared3agent-memory
2952604.201172026-04-22recent-2026-Apr-JulTo Know is to Construct: Schema-Constrained Generation for Agent Memoryhttps://arxiv.org/abs/2604.20117Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_gui5agent-memory
2962604.201832026-04-22recent-2026-Apr-JulDual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solvinghttps://arxiv.org/abs/2604.20183Truecoreexecution_statemodelrepresentation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal4agent-memory
2972604.203002026-04-22recent-2026-Apr-JulFSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memoryhttps://arxiv.org/abs/2604.20300Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trustupdate_forgetting5agent-memory
2982604.205822026-04-22recent-2026-Apr-JulTrust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agentshttps://arxiv.org/abs/2604.20582Truecoreexecution_statemodelsecurity_privacy_trustsecurity_governance4agent-memory
2992604.205982026-04-22recent-2026-Apr-JulSelf-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledgehttps://arxiv.org/abs/2604.20598Falsecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;systems_efficiency6agent-memory
3002604.220852026-04-23recent-2026-Apr-JulMemanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agentshttps://arxiv.org/abs/2604.22085Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;systems_efficiencyretrieval_representation;execution_multimodal3agent-memory
3012604.237112026-04-26recent-2026-Apr-JulSpore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probinghttps://arxiv.org/abs/2604.23711Falsecoreexecution_statemodelretrieval_access;evaluation_diagnosis;security_privacy_trust;systems_efficiencysecurity_governance;systems_efficiency4agent-memory
3022606.205702026-04-26recent-2026-Apr-JulInfrastructure for the Agentic Web: Gap Analysis and Architecture from the Agentverse Platformhttps://arxiv.org/abs/2606.20570Falsecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;retrieval_representation1agent-memory
3032604.261972026-04-29recent-2026-Apr-JulHierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agenthttps://arxiv.org/abs/2604.26197Truecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation5long-term-memory
3042604.266222026-04-29recent-2026-Apr-JulOCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memoryhttps://arxiv.org/abs/2604.26622Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal3agent-memory
3052604.270032026-04-29recent-2026-Apr-JulWhen Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agentshttps://arxiv.org/abs/2604.27003Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy3procedural-memory
3062604.270452026-04-29recent-2026-Apr-JulDetecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecturehttps://arxiv.org/abs/2604.27045Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust5agent-memory
3072604.272832026-04-30recent-2026-Apr-JulLearning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agentshttps://arxiv.org/abs/2604.27283Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;systems_efficiencyretrieval_representation;experience_skill_policy3agent-memory
3082604.277072026-04-30recent-2026-Apr-JulContextual Agentic Memory is a Memo, Not True Memoryhttps://arxiv.org/abs/2604.27707Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiency3agent-memory
3092604.279962026-04-30recent-2026-Apr-JulExploring LLM Agent Designs and Interaction Modalities for Scientific Visualizationhttps://arxiv.org/abs/2604.27996Falsecoreupdate_forgettingmodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency4long-term-memory
3102605.007022026-05-01recent-2026-Apr-JulLearning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memoryhttps://arxiv.org/abs/2605.00702Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy4memory-evaluation
3112605.013862026-05-02recent-2026-Apr-JulMemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agentshttps://arxiv.org/abs/2605.01386Truecorerepresentationmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;experience_skill_policy2long-term-memory
3122605.019702026-05-03recent-2026-Apr-JulTrojan Hippo: Weaponizing Agent Memory for Data Exfiltrationhttps://arxiv.org/abs/2605.01970Truecoreupdate_forgettingmodelevaluation_diagnosis;security_privacy_trust;systems_efficiency4agent-memory;long-term-memory
3132605.021992026-05-04recent-2026-Apr-JulMEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writinghttps://arxiv.org/abs/2605.02199Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;systems_efficiency3long-term-memory
3142605.032282026-05-04recent-2026-Apr-JulMAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memoryhttps://arxiv.org/abs/2605.03228Truecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosis;security_privacy_trustexecution_multimodal5agent-memory
3152605.033122026-05-05recent-2026-Apr-JulMemFlow: Intent-Driven Memory Orchestration for Small Language Model Agentshttps://arxiv.org/abs/2605.03312Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;systems_efficiency7agent-memory;memory-evaluation
3162605.033542026-05-05recent-2026-Apr-JulWhat Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosishttps://arxiv.org/abs/2605.03354Truecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis5agent-memory
3172605.038042026-05-05recent-2026-Apr-JulScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgettinghttps://arxiv.org/abs/2605.03804Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;multimodal_embodied_gui;systems_efficiencyupdate_forgetting;systems_efficiency;personal_shared4agent-memory;episodic-memory;long-term-memory
3182605.067022026-05-05recent-2026-Apr-JulCASCADE: Case-Based Continual Adaptation for Large Language Models During Deploymenthttps://arxiv.org/abs/2605.06702Falsecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy5episodic-memory
3192605.048112026-05-06recent-2026-Apr-JulTree-based Credit Assignment for Multi-Agent Memory Systemhttps://arxiv.org/abs/2605.04811Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;systems_efficiencyexperience_skill_policy;personal_shared5agent-memory
3202605.048972026-05-06recent-2026-Apr-JulStorage Is Not Memory: A Retrieval-Centered Architecture for Agent Recallhttps://arxiv.org/abs/2605.04897Truecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencyretrieval_representation;systems_efficiency3agent-memory
3212605.055832026-05-07recent-2026-Apr-JulBelief Memory: Agent Memory Under Partial Observabilityhttps://arxiv.org/abs/2605.05583Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis5agent-memory
3222605.061322026-05-07recent-2026-Apr-JulMemReranker: Reasoning-Aware Reranking for Agent Memory Retrievalhttps://arxiv.org/abs/2605.06132Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis;systems_efficiencyretrieval_representation7agent-memory
3232605.065272026-05-07recent-2026-Apr-JulSTALE: Can LLM Agents Know When Their Memories Are No Longer Valid?https://arxiv.org/abs/2605.06527Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyupdate_forgetting7agent-memory
3242605.067162026-05-07recent-2026-Apr-JulFrom Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismshttps://arxiv.org/abs/2605.06716Truecoreexperience_learningmodelretrieval_access;execution_state;experience_skill_learning;systems_efficiencybenchmark_diagnosis;experience_skill_policy;systems_efficiency0agent-memory
3252605.068122026-05-07recent-2026-Apr-JulTowards Security-Auditable LLM Agents: A Unified Graph Representationhttps://arxiv.org/abs/2605.06812Falsecoresecurity_privacymodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multi_agent_sharedretrieval_representation;security_governance3long-term-memory
3262605.072422026-05-08recent-2026-Apr-JulMEMOREPAIR: Barrier-First Cascade Repair in Agentic Memoryhttps://arxiv.org/abs/2605.07242Truecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiency8agent-memory
3272605.073132026-05-08recent-2026-Apr-JulWhen Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memoryhttps://arxiv.org/abs/2605.07313Truesupportingevaluationmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis3agent-memory
3282605.083742026-05-08recent-2026-Apr-JulMemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGshttps://arxiv.org/abs/2605.08374Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiexperience_skill_policy;security_governance3agent-memory;episodic-memory
3292605.084422026-05-08recent-2026-Apr-JulDefense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agentshttps://arxiv.org/abs/2605.08442Truesupportingsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;security_governance7long-term-memory
3302605.084682026-05-08recent-2026-Apr-JulPYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agentshttps://arxiv.org/abs/2605.08468Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;systems_efficiencyretrieval_representation5episodic-memory
3312605.085382026-05-08recent-2026-Apr-JulHuman-Inspired Memory Architecture for LLM Agentshttps://arxiv.org/abs/2605.08538Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiency8long-term-memory
3322605.090332026-05-09recent-2026-Apr-JulShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflictshttps://arxiv.org/abs/2605.09033Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trustretrieval_representation;security_governance7agent-memory
3332605.093152026-05-10recent-2026-Apr-JulDo Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptationhttps://arxiv.org/abs/2605.09315Truecoreupdate_forgettingmodelupdate_forgetting;execution_state;experience_skill_learning;systems_efficiencyupdate_forgetting;experience_skill_policy0long-term-memory
3342605.093302026-05-10recent-2026-Apr-JulThe Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memoryhttps://arxiv.org/abs/2605.09330Truesupportingevaluationmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiency2agent-memory
3352605.110322026-05-10recent-2026-Apr-JulPortable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agentshttps://arxiv.org/abs/2605.11032Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;security_privacy_trust;systems_efficiencyretrieval_representation1agent-memory
3362605.098632026-05-11recent-2026-Apr-JulNautilus Compass: Black-box Persona Drift Detection for Production LLM Agentshttps://arxiv.org/abs/2605.09863Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;systems_efficiency7agent-memory
3372605.099422026-05-11recent-2026-Apr-JulHAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolutionhttps://arxiv.org/abs/2605.09942Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;multi_agent_sharedretrieval_representation;experience_skill_policy3agent-memory
3382605.102682026-05-11recent-2026-Apr-JulMemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereadinghttps://arxiv.org/abs/2605.10268Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexecution_multimodal5agent-memory
3392605.108702026-05-11recent-2026-Apr-JulRemember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memoryhttps://arxiv.org/abs/2605.10870Truecoreupdate_forgettingmodelupdate_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiency3agent-memory
3402605.108992026-05-11recent-2026-Apr-JulRubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardshttps://arxiv.org/abs/2605.10899Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;execution_multimodal4agent-memory
3412605.138802026-05-11recent-2026-Apr-JulPREPING: Building Agent Memory without Taskshttps://arxiv.org/abs/2605.13880Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;multimodal_embodied_gui;systems_efficiency5agent-memory
3422605.118142026-05-12recent-2026-Apr-JulMedMemoryBench: Benchmarking Agent Memory in Personalized Healthcarehttps://arxiv.org/abs/2605.11814Truecoreexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;personal_shared3agent-memory
3432605.120612026-05-12recent-2026-Apr-JulSAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memoryhttps://arxiv.org/abs/2605.12061Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosisretrieval_representation;experience_skill_policy2agent-memory;long-term-memory;memory-evaluation
3442605.122132026-05-12recent-2026-Apr-JulGoal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systemshttps://arxiv.org/abs/2605.12213Truecoreupdate_forgettingmodelretrieval_access;execution_stateretrieval_representation5agent-memory
3452605.122942026-05-12recent-2026-Apr-JulExecutable Agentic Memory for GUI Agenthttps://arxiv.org/abs/2605.12294Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;multimodal_embodied_gui;systems_efficiencyexecution_multimodal2agent-memory
3462605.124932026-05-12recent-2026-Apr-JulLongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagueshttps://arxiv.org/abs/2605.12493Truecoreexperience_learningmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;experience_skill_policy8agent-memory;memory-evaluation
3472605.129782026-05-13recent-2026-Apr-JulUseful Memories Become Faulty When Continuously Updated by LLMshttps://arxiv.org/abs/2605.12978Truecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosisupdate_forgetting6agent-memory
3482605.134382026-05-13recent-2026-Apr-JulCogniFold: Always-On Proactive Memory via Cognitive Foldinghttps://arxiv.org/abs/2605.13438Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis3agent-memory
3492605.135422026-05-13recent-2026-Apr-JulRealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitationhttps://arxiv.org/abs/2605.13542Falsecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosisbenchmark_diagnosis4agent-memory
3502605.139412026-05-13recent-2026-Apr-JulEvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agentshttps://arxiv.org/abs/2605.13941Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosisretrieval_representation;experience_skill_policy8long-term-memory
3512605.144212026-05-14recent-2026-Apr-JulMemLineage: Lineage-Guided Enforcement for LLM Agent Memoryhttps://arxiv.org/abs/2605.14421Truesupportingsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiexecution_multimodal5agent-memory
3522605.144982026-05-14recent-2026-Apr-JulGroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversationshttps://arxiv.org/abs/2605.14498Truesupportingevaluationmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guibenchmark_diagnosis7agent-memory
3532605.149062026-05-14recent-2026-Apr-JulMemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Modelshttps://arxiv.org/abs/2605.14906Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal6agent-memory
3542605.151282026-05-14recent-2026-Apr-JulMemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memoryhttps://arxiv.org/abs/2605.15128Truesupportingevaluationmodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal3agent-memory
3552605.153382026-05-14recent-2026-Apr-JulHidden in Memory: Sleeper Memory Poisoning in LLM Agentshttps://arxiv.org/abs/2605.15338Truesupportingsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trustsecurity_governance4long-term-memory
3562605.157012026-05-15recent-2026-Apr-JulH-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structurehttps://arxiv.org/abs/2605.15701Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencyretrieval_representation;experience_skill_policy2agent-memory;memory-evaluation
3572605.157102026-05-15recent-2026-Apr-JulSMMBench: A Benchmark for Source-Distributed Multimodal Agent Memoryhttps://arxiv.org/abs/2605.15710Truesupportingevaluationmodelretrieval_access;update_forgetting;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;execution_multimodal4agent-memory;memory-evaluation
3582605.157592026-05-15recent-2026-Apr-JulDimMem: Dimensional Structuring for Efficient Long-Term Agent Memoryhttps://arxiv.org/abs/2605.15759Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencysystems_efficiency5agent-memory;long-term-memory
3592605.162332026-05-15recent-2026-Apr-JulFORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcasthttps://arxiv.org/abs/2605.16233Truesupportingevaluationmodelrepresentation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiencyupdate_forgetting;experience_skill_policy8agent-memory
3602605.164812026-05-15recent-2026-Apr-JulVisual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrievalhttps://arxiv.org/abs/2605.16481Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;multimodal_embodied_guiretrieval_representation;execution_multimodal5agent-memory
3612605.167462026-05-16recent-2026-Apr-JulState Contamination in Memory-Augmented LLM Agentshttps://arxiv.org/abs/2605.16746Truesupportingsecurity_privacymodelretrieval_access;representation_organization;update_forgetting;execution_state;security_privacy_trust;multi_agent_shared;systems_efficiencysecurity_governance6long-term-memory
3622605.168582026-05-16recent-2026-Apr-JulPedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicleshttps://arxiv.org/abs/2605.16858Falsecoreexecution_statemodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis7episodic-memory
3632605.239862026-05-16recent-2026-Apr-JulMemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexinghttps://arxiv.org/abs/2605.23986Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation;systems_efficiency8agent-memory;memory-evaluation
3642605.173482026-05-17recent-2026-Apr-JulTaming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolutionhttps://arxiv.org/abs/2605.17348Falsecoreupdate_forgettingmodelmulti_agent_shared;systems_efficiencypersonal_shared5agent-memory
3652605.175962026-05-17recent-2026-Apr-JulNeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agentshttps://arxiv.org/abs/2605.17596Truecoreupdate_forgettingmodelretrieval_access;representation_organization;security_privacy_trust0long-term-memory
3662605.176252026-05-17recent-2026-Apr-JulEpisodic-Semantic Memory Architecture for Long-Horizon Scientific Agentshttps://arxiv.org/abs/2605.17625Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;systems_efficiencyexecution_multimodal7agent-memory
3672605.176412026-05-17recent-2026-Apr-JulCausal Intervention-Based Memory Selection for Long-Horizon LLM Agentshttps://arxiv.org/abs/2605.17641Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisexecution_multimodal6long-term-memory
3682605.182842026-05-18recent-2026-Apr-JulCommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositorieshttps://arxiv.org/abs/2605.18284Truecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;systems_efficiency6agent-memory
3692605.184212026-05-18recent-2026-Apr-JulEvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivehttps://arxiv.org/abs/2605.18421Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy6agent-memory;long-term-memory
3702605.186522026-05-18recent-2026-Apr-JulMementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agentshttps://arxiv.org/abs/2605.18652Truecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;execution_multimodal5agent-memory
3712605.189302026-05-18recent-2026-Apr-JulOEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experienceshttps://arxiv.org/abs/2605.18930Falsecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trustexperience_skill_policy;security_governance6agent-memory
3722605.199522026-05-19recent-2026-Apr-JulRethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memoryhttps://arxiv.org/abs/2605.19952Truecoreupdate_forgettingmodelretrieval_access;representation_organization;systems_efficiencybenchmark_diagnosis6agent-memory
3732605.206162026-05-20recent-2026-Apr-JulAuto-Dreamer: Learning Offline Memory Consolidation for Language Agentshttps://arxiv.org/abs/2605.20616Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;security_privacy_trustupdate_forgetting;experience_skill_policy4agent-memory
3742605.207242026-05-20recent-2026-Apr-JulCALMem : Application-Layer Dual Memory for Conversational AIhttps://arxiv.org/abs/2605.20724Truecoreexecution_statemodelretrieval_access;representation_organization;multimodal_embodied_gui;systems_efficiency0episodic-memory
3752605.208332026-05-20recent-2026-Apr-JulMemGym: a Long-Horizon Memory Environment for LLM Agentshttps://arxiv.org/abs/2605.20833Truecoreexecution_statemodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal3agent-memory;memory-evaluation
3762605.214632026-05-20recent-2026-Apr-JulMem-$π$: Adaptive Memory through Learning When and What to Generatehttps://arxiv.org/abs/2605.21463Truecoreexecution_statemodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy6episodic-memory
3772605.224112026-05-21recent-2026-Apr-JulDeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QAhttps://arxiv.org/abs/2605.22411Truecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;systems_efficiencyexperience_skill_policy2long-term-memory
3782605.227212026-05-21recent-2026-Apr-JulSelf-Evolving Multi-Agent Systems via Decentralized Memoryhttps://arxiv.org/abs/2605.22721Truecoreexecution_statemodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;personal_shared6long-term-memory
3792605.230672026-05-21recent-2026-Apr-JulWhat Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QAhttps://arxiv.org/abs/2605.23067Truecoreexecution_statemodelexperience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy3agent-memory
3802605.237232026-05-22recent-2026-Apr-JulMemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detectionhttps://arxiv.org/abs/2605.23723Truecoreexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;security_privacy_trustsecurity_governance2agent-memory;long-term-memory
3812605.249412026-05-24recent-2026-Apr-JulMemory-Induced Tool-Drift in LLM Agentshttps://arxiv.org/abs/2605.24941Truecoreexecution_statemodelevaluation_diagnosis;security_privacy_trust;systems_efficiency5long-term-memory
3822605.250022026-05-24recent-2026-Apr-JulMemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systemshttps://arxiv.org/abs/2605.25002Truecoreexecution_statemodelupdate_forgetting;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiency5agent-memory
3832605.261542026-05-24recent-2026-Apr-JulMemMorph: Tool Hijacking in LLM Agents via Memory Poisoninghttps://arxiv.org/abs/2605.26154Truecoreexecution_statemodelexperience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guisecurity_governance6long-term-memory
3842605.258692026-05-25recent-2026-Apr-JulMitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representationhttps://arxiv.org/abs/2605.25869Truecoreexecution_statemodelretrieval_access;representation_organization;security_privacy_trust;systems_efficiencyretrieval_representation;security_governance5long-term-memory
3852605.262522026-05-25recent-2026-Apr-JulIs Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memoryhttps://arxiv.org/abs/2605.26252Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;security_privacy_trust;systems_efficiencybenchmark_diagnosis;retrieval_representation1agent-memory
3862605.262562026-05-25recent-2026-Apr-JulPersonalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactionshttps://arxiv.org/abs/2605.26256Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal;personal_shared2episodic-memory
3872605.273662026-05-26recent-2026-Apr-JulMUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluationhttps://arxiv.org/abs/2605.27366Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis;experience_skill_policy6agent-memory
3882605.277602026-05-26recent-2026-Apr-JulSkillGrad: Optimizing Agent Skills Like Gradient Descenthttps://arxiv.org/abs/2605.27760Falsecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosisexperience_skill_policy5long-term-memory
3892605.277622026-05-26recent-2026-Apr-JulPEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecrafthttps://arxiv.org/abs/2605.27762Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiexperience_skill_policy;execution_multimodal5agent-memory
3902605.278252026-05-27recent-2026-Apr-JulMRMMIA: Membership Inference Attacks on Memory in Chat Agentshttps://arxiv.org/abs/2605.27825Truecoresecurity_privacymodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trustsecurity_governance4agent-memory
3912605.280462026-05-27recent-2026-Apr-JulMemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agentshttps://arxiv.org/abs/2605.28046Truecoreexecution_statemodelretrieval_access;evaluation_diagnosis;multimodal_embodied_gui4agent-memory
3922605.293412026-05-28recent-2026-Apr-JulWorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interactionhttps://arxiv.org/abs/2605.29341Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal5agent-memory
3932605.296302026-05-28recent-2026-Apr-JulEntity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memoryhttps://arxiv.org/abs/2605.29630Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation7agent-memory;memory-evaluation
3942605.296402026-05-28recent-2026-Apr-JulVikingMem: A Memory Base Management System for Stateful LLM-based Applicationshttps://arxiv.org/abs/2605.29640Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiency6agent-memory;memory-evaluation
3952605.299602026-05-28recent-2026-Apr-JulHijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interactionhttps://arxiv.org/abs/2605.29960Truecoreupdate_forgettingmodelevaluation_diagnosis;security_privacy_trustsecurity_governance5agent-memory;long-term-memory
3962605.300582026-05-28recent-2026-Apr-JulHEART-Bench: Do LLM Agents Exhibit Human-like Psychology?https://arxiv.org/abs/2605.30058Falsecoreexperience_learningmodelrepresentation_organization;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_gui2episodic-memory
3972605.306212026-05-28recent-2026-Apr-JulHarness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agentshttps://arxiv.org/abs/2605.30621Falsecoreupdate_forgettingmodelupdate_forgetting;execution_state;experience_skill_learning;systems_efficiencyexperience_skill_policy2procedural-memory
3982607.000172026-05-28recent-2026-Apr-JulLearning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memoryhttps://arxiv.org/abs/2607.00017Truecoreexperience_learningmodelretrieval_access;evaluation_diagnosis;multimodal_embodied_guiretrieval_representation;experience_skill_policy;personal_shared5long-term-memory
3992605.306902026-05-29recent-2026-Apr-JulElasticMem: Latent Memory as a Learnable Resource for LLM Agentshttps://arxiv.org/abs/2605.30690Truecorerepresentationmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy8long-term-memory
4002605.307112026-05-29recent-2026-Apr-JulSAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMshttps://arxiv.org/abs/2605.30711Truecorerepresentationmodelretrieval_access;systems_efficiencysystems_efficiency3agent-memory
4012605.308582026-05-29recent-2026-Apr-JulForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memoryhttps://arxiv.org/abs/2605.30858Truecorerepresentationmodelretrieval_access;representation_organization;experience_skill_learning;multimodal_embodied_guiexperience_skill_policy;execution_multimodal2agent-memory
4022605.310752026-05-29recent-2026-Apr-JulTask-Focused Memorization for Multimodal Agentshttps://arxiv.org/abs/2605.31075Truecorerepresentationmodelexperience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal4agent-memory
4032606.006192026-05-30recent-2026-Apr-JulMemPro: Agentic Memory Systems as Evolvable Programshttps://arxiv.org/abs/2606.00619Truecorerepresentationmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy6agent-memory
4042606.007342026-05-30recent-2026-Apr-JulEMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updateshttps://arxiv.org/abs/2606.00734Falsecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;update_forgetting4agent-memory
4052606.007562026-05-30recent-2026-Apr-JulCoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systemshttps://arxiv.org/abs/2606.00756Truecorerepresentationmodelrepresentation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;systems_efficiency;personal_shared2long-term-memory
4062606.011382026-05-31recent-2026-Apr-Julmemorywire: A Vendor-Neutral Wire Format for Agent Memory Operationshttps://arxiv.org/abs/2606.01138Truecorerepresentationmodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;systems_efficiencysystems_efficiency6agent-memory
4072606.015282026-06-01recent-2026-Apr-JulJoint Agent Memory and Exploration Learning via Novelty Signalshttps://arxiv.org/abs/2606.01528Truecorerepresentationmodelevaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy5agent-memory
4082606.017222026-06-01recent-2026-Apr-JulPost-Deterministic Distributed Systems: A New Foundation for Trustworthy Autonomous Infrastructurehttps://arxiv.org/abs/2606.01722Falsecorerepresentationmodelretrieval_access;representation_organization;security_privacy_trust;multimodal_embodied_guiretrieval_representation;security_governance1agent-memory
4092606.028122026-06-01recent-2026-Apr-JulTraj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detectionhttps://arxiv.org/abs/2606.02812Falsecorerepresentationmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_guiexperience_skill_policy;personal_shared3agent-memory
4102606.031972026-06-02recent-2026-Apr-JulMemTrain: Self-Supervised Context Memory Traininghttps://arxiv.org/abs/2606.03197Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiency4agent-memory
4112606.033292026-06-02recent-2026-Apr-JulInfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gainhttps://arxiv.org/abs/2606.03329Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;systems_efficiency5agent-memory
4122606.033742026-06-02recent-2026-Apr-JuleMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agentshttps://arxiv.org/abs/2606.03374Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal6agent-memory;memory-evaluation
4132606.041202026-06-02recent-2026-Apr-JulSaliMory: Orchestrating Cognitive Memory for Conversational Agentshttps://arxiv.org/abs/2606.04120Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning5agent-memory
4142606.043152026-06-03recent-2026-Apr-JulExploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baselinehttps://arxiv.org/abs/2606.04315Truecoreexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis2agent-memory
4152606.043292026-06-03recent-2026-Apr-JulFrom Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agentshttps://arxiv.org/abs/2606.04329Truecoresecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trustbenchmark_diagnosis;security_governance3long-term-memory
4162606.045552026-06-03recent-2026-Apr-JulTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agentshttps://arxiv.org/abs/2606.04555Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;systems_efficiencyexecution_multimodal4agent-memory;memory-evaluation
4172606.046282026-06-03recent-2026-Apr-JulRAMPART: Registry-based Agentic Memory with Priority-Aware Runtime Transformationhttps://arxiv.org/abs/2606.04628Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;systems_efficiencysystems_efficiency6agent-memory
4182606.047802026-06-03recent-2026-Apr-JulPersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agentshttps://arxiv.org/abs/2606.04780Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;update_forgetting3agent-memory;long-term-memory;memory-evaluation
4192606.055132026-06-03recent-2026-Apr-JulEpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shiftshttps://arxiv.org/abs/2606.05513Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;security_privacy_trustexperience_skill_policy5episodic-memory
4202606.283492026-06-03recent-2026-Apr-JulHMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoninghttps://arxiv.org/abs/2606.28349Truecorerepresentationmodelretrieval_access;representation_organization;evaluation_diagnosis;multi_agent_sharedretrieval_representation;personal_shared4agent-memory
4212606.056462026-06-04recent-2026-Apr-JulEnhancing Software Engineering Through Closed-Loop Memory Optimizationhttps://arxiv.org/abs/2606.05646Truecoreupdate_forgettingmodelexperience_skill_learning;evaluation_diagnosis;systems_efficiency4episodic-memory
4222606.056842026-06-04recent-2026-Apr-JulAdaMEM: Test-Time Adaptive Memory for Language Agentshttps://arxiv.org/abs/2606.05684Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy6agent-memory
4232606.060542026-06-04recent-2026-Apr-JulBeyond Similarity: Trustworthy Memory Search for Personal AI Agentshttps://arxiv.org/abs/2606.06054Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation;security_governance2agent-memory
4242606.060902026-06-04recent-2026-Apr-JulBeyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agentshttps://arxiv.org/abs/2606.06090Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal6agent-memory
4252606.062402026-06-04recent-2026-Apr-JulTOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memoryhttps://arxiv.org/abs/2606.06240Truecoreupdate_forgettingmodelupdate_forgetting;security_privacy_trust2long-term-memory
4262606.064482026-06-04recent-2026-Apr-JulAgent Memory: Characterization and System Implications of Stateful Long-Horizon Workloadshttps://arxiv.org/abs/2606.06448Truecoreexecution_statemodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;systems_efficiencyexecution_multimodal2agent-memory
4272606.074022026-06-05recent-2026-Apr-JulM$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactionshttps://arxiv.org/abs/2606.07402Truecoreaccessmodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal4memory-evaluation
4282606.099002026-06-05recent-2026-Apr-JulLess Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full Historyhttps://arxiv.org/abs/2606.09900Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencyretrieval_representation7long-term-memory;memory-evaluation
4292606.248962026-06-05recent-2026-Apr-JulWhy Memory Components Fail: Eight Years of License and Sustainability Events in Open-Source Data Infrastructurehttps://arxiv.org/abs/2606.24896Truecoreaccessmodelrepresentation_organization;experience_skill_learning;security_privacy_trustretrieval_representation1agent-memory
4302606.083672026-06-06recent-2026-Apr-JulEmergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomyhttps://arxiv.org/abs/2606.08367Falsecoreexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;security_privacy_trust;multi_agent_sharedbenchmark_diagnosis;execution_multimodal;personal_shared3long-term-memory
4312606.091982026-06-08recent-2026-Apr-JulMASS: Deep Research for Social Sciences with Memory-Augmented Social Simulationhttps://arxiv.org/abs/2606.09198Truecoreexperience_learningmodelretrieval_access;representation_organization;update_forgetting;execution_state;multimodal_embodied_guiretrieval_representation4agent-memory
4322606.094612026-06-08recent-2026-Apr-JulH2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactionshttps://arxiv.org/abs/2606.09461Truecorerepresentationmodelretrieval_access;update_forgetting;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;execution_multimodal3memory-evaluation
4332606.094832026-06-08recent-2026-Apr-JulMemory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agentshttps://arxiv.org/abs/2606.09483Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;experience_skill_learning;evaluation_diagnosisretrieval_representation;experience_skill_policy2agent-memory;long-term-memory
4342606.097742026-06-08recent-2026-Apr-JulAuto-Configuring Scientific Simulators with Lightweight Coding-Agent Adaptershttps://arxiv.org/abs/2606.09774Falsecoreexecution_statemodelretrieval_access;experience_skill_learning;systems_efficiencyexperience_skill_policy2agent-memory
4352606.100622026-06-08recent-2026-Apr-JulDeployment-Time Memorization in Foundation-Model Agentshttps://arxiv.org/abs/2606.10062Truesupportingevaluationmodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiency5agent-memory
4362606.102992026-06-09recent-2026-Apr-JulWhat Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memoryhttps://arxiv.org/abs/2606.10299Truecoreexecution_statemodelretrieval_accessexecution_multimodal7agent-memory
4372606.104232026-06-09recent-2026-Apr-JulWebChallenger: A Reliable and Efficient Generalist Web Agenthttps://arxiv.org/abs/2606.10423Falsecoreexecution_statemodelrepresentation_organization;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;systems_efficiency4long-term-memory
4382606.105322026-06-09recent-2026-Apr-JulActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoninghttps://arxiv.org/abs/2606.10532Truecoreexecution_statemodelretrieval_access;update_forgetting;execution_stateexecution_multimodal3agent-memory
4392606.105772026-06-09recent-2026-Apr-JulAgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harnesshttps://arxiv.org/abs/2606.10577Falsecoreexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal6agent-memory
4402606.106772026-06-09recent-2026-Apr-JulInfini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memoryhttps://arxiv.org/abs/2606.10677Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation3agent-memory;long-term-memory
4412606.116802026-06-10recent-2026-Apr-JulOrganize then Retrieve: Hierarchical Memory Navigation for Efficient Agentshttps://arxiv.org/abs/2606.11680Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyretrieval_representation;execution_multimodal;systems_efficiency5agent-memory
4422606.122902026-06-10recent-2026-Apr-JulSelection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrievalhttps://arxiv.org/abs/2606.12290Truecoreexecution_statemodelretrieval_access;representation_organization;security_privacy_trust;systems_efficiencyretrieval_representation;security_governance0agent-memory
4432606.127032026-06-10recent-2026-Apr-JulSMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systemshttps://arxiv.org/abs/2606.12703Truecoreexecution_statemodelretrieval_access;evaluation_diagnosis;security_privacy_trustsecurity_governance;systems_efficiency3long-term-memory
4442606.128522026-06-11recent-2026-Apr-JulWISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoninghttps://arxiv.org/abs/2606.12852Falsecoreexecution_statemodelretrieval_access;representation_organization;execution_state;multimodal_embodied_guiexecution_multimodal3episodic-memory
4452606.129452026-06-11recent-2026-Apr-JulLearning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memoryhttps://arxiv.org/abs/2606.12945Truecoreexecution_statemodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencyexperience_skill_policy9agent-memory
4462606.131772026-06-11recent-2026-Apr-JulMemRefine: LLM-Guided Compression for Long-Term Agent Memoryhttps://arxiv.org/abs/2606.13177Truecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal;systems_efficiency4agent-memory
4472606.133922026-06-11recent-2026-Apr-JulMiniMax Sparse Attentionhttps://arxiv.org/abs/2606.13392Falsesupportingexecution_statemodelretrieval_access;representation_organization;multimodal_embodied_gui;systems_efficiency4long-term-memory
4482606.144702026-06-12recent-2026-Apr-JulGitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Mergehttps://arxiv.org/abs/2606.14470Truesupportingexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiency6agent-memory
4492606.145712026-06-12recent-2026-Apr-JulStreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistancehttps://arxiv.org/abs/2606.14571Truesupportingexecution_statemodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosisbenchmark_diagnosis4agent-memory;memory-evaluation
4502606.150712026-06-13recent-2026-Apr-JulQuantum learning with a single-atom sensorhttps://arxiv.org/abs/2606.15071Falsesupportingexecution_statemodelsystems_efficiencyexperience_skill_policy0agent-memory
4512606.156092026-06-14recent-2026-Apr-JulFragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusionhttps://arxiv.org/abs/2606.15609Truesupportingexecution_statemodelretrieval_access;evaluation_diagnosis;security_privacy_trust6agent-memory;long-term-memory
4522606.159032026-06-14recent-2026-Apr-JulControl-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurationshttps://arxiv.org/abs/2606.15903Truesupportingexecution_statemodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis;update_forgetting8agent-memory
4532606.169032026-06-15recent-2026-Apr-JulDirectory-Aware Query and Maintenance in Vector Databaseshttps://arxiv.org/abs/2606.16903Falsesupportingexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiencyretrieval_representation4agent-memory
4542606.173282026-06-15recent-2026-Apr-JulMemTrace: Probing What Final Accuracy Misses in Long-Term Memoryhttps://arxiv.org/abs/2606.17328Truesupportingexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;systems_efficiency4long-term-memory
4552606.176282026-06-16recent-2026-Apr-JulOPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillationhttps://arxiv.org/abs/2606.17628Falsesupportingexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosisexperience_skill_policy4agent-memory
4562606.183562026-06-16recent-2026-Apr-JulSafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agentshttps://arxiv.org/abs/2606.18356Falsesupportingexecution_statemodelrepresentation_organization;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui7long-term-memory
4572606.184062026-06-16recent-2026-Apr-JulCoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agentshttps://arxiv.org/abs/2606.18406Truesupportingexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyretrieval_representation;experience_skill_policy;execution_multimodal5agent-memory
4582606.187462026-06-17recent-2026-Apr-JulWhat Must Generalist Agents Remember?https://arxiv.org/abs/2606.18746Truecoreexperience_learningmodelexecution_state0agent-memory
4592606.188292026-06-17recent-2026-Apr-JulGateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agentshttps://arxiv.org/abs/2606.18829Truesupportingshared_memorymodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis;security_governance5agent-memory;memory-evaluation
4602606.189502026-06-17recent-2026-Apr-JulRTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Modelshttps://arxiv.org/abs/2606.18950Falsesupportingupdate_forgettingmodelrepresentation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multi_agent_sharedbenchmark_diagnosis3agent-memory
4612606.194092026-06-17recent-2026-Apr-JulOpenRath: Session-Centered Runtime State for Agent Systemshttps://arxiv.org/abs/2606.19409Falsecorerepresentationmodelevaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencysystems_efficiency3agent-memory
4622606.198472026-06-18recent-2026-Apr-JulAtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Factshttps://arxiv.org/abs/2606.19847Truecorerepresentationmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiency2long-term-memory
4632606.198572026-06-18recent-2026-Apr-JulLarge Language Models Do Not Always Need Readable Languagehttps://arxiv.org/abs/2606.19857Falsesupportingrepresentationmodelrepresentation_organization;evaluation_diagnosis;multi_agent_shared;systems_efficiency4agent-memory
4642606.200472026-06-18recent-2026-Apr-JulPACMS: Submodular Context Selection as a Pluggable Engine for LLM Agentshttps://arxiv.org/abs/2606.20047Falsesupportingupdate_forgettingmodelretrieval_access;systems_efficiency2long-term-memory
4652606.205152026-06-18recent-2026-Apr-JulS-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligencehttps://arxiv.org/abs/2606.20515Falsecorerepresentationmodelrepresentation_organization;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal6agent-memory
4662606.209542026-06-18recent-2026-Apr-JulLearning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learninghttps://arxiv.org/abs/2606.20954Truecorerepresentationmodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;systems_efficiencyupdate_forgetting;experience_skill_policy;execution_multimodal8agent-memory
4672606.211442026-06-19recent-2026-Apr-JulAdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agentshttps://arxiv.org/abs/2606.21144Truecorerepresentationmodelrepresentation_organization;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;systems_efficiencyexperience_skill_policy;execution_multimodal;personal_shared5long-term-memory
4682606.215622026-06-19recent-2026-Apr-JulCompressing Observation History into Agent Memory: Distilling Transformers into Recurrent Transformershttps://arxiv.org/abs/2606.21562Truesupportingrepresentationmodelrepresentation_organization;execution_state;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;systems_efficiency2agent-memory
4692606.216492026-06-19recent-2026-Apr-JulEvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memoryhttps://arxiv.org/abs/2606.21649Truesupportingrepresentationmodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosisretrieval_representation;experience_skill_policy6agent-memory
4702606.220302026-06-20recent-2026-Apr-JulNous: A Predictive World Model for Long-Term Agent Memoryhttps://arxiv.org/abs/2606.22030Truecoreexperience_learningmodelrepresentation_organization;update_forgetting;evaluation_diagnosis;systems_efficiency5agent-memory;memory-evaluation
4712606.222632026-06-20recent-2026-Apr-JulRevelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebaseshttps://arxiv.org/abs/2606.22263Truesupportingsecurity_privacymodelevaluation_diagnosis;security_privacy_trust;systems_efficiencysecurity_governance;systems_efficiency5agent-memory
4722606.228442026-06-22recent-2026-Apr-JulRaMem: Contextual Reinstatement for Long-term Agentic Memoryhttps://arxiv.org/abs/2606.22844Truecoreexecution_statemodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis7agent-memory;long-term-memory;memory-evaluation
4732606.228772026-06-22recent-2026-Apr-JulDynamicMem: A Long-Horizon Memory Benchmark in Real-World Settingshttps://arxiv.org/abs/2606.22877Truesupportingsecurity_privacymodelretrieval_access;update_forgetting;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiencybenchmark_diagnosis;execution_multimodal6memory-evaluation
4742606.231272026-06-22recent-2026-Apr-JulManaging Procedural Memory in LLM Agents: Control, Adaptation, and Evaluationhttps://arxiv.org/abs/2606.23127Truecoreevaluationmodelexperience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis;experience_skill_policy7procedural-memory
4752606.231952026-06-22recent-2026-Apr-JulMemory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memoryhttps://arxiv.org/abs/2606.23195Truesupportingsecurity_privacymodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guibenchmark_diagnosis4agent-memory
4762606.232832026-06-22recent-2026-Apr-JulTowards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMshttps://arxiv.org/abs/2606.23283Truecoreexecution_statemodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis;retrieval_representation;personal_shared5agent-memory
4772606.243222026-06-23recent-2026-Apr-JulSecuring LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guaranteeshttps://arxiv.org/abs/2606.24322Truesupportingsecurity_privacymodelretrieval_access;evaluation_diagnosis;security_privacy_trustsecurity_governance6agent-memory;long-term-memory
4782606.245352026-06-23recent-2026-Apr-JulGoverned Shared Memory for Multi-Agent LLM Systemshttps://arxiv.org/abs/2606.24535Truecoreshared_memorymodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;multi_agent_shared;systems_efficiencysecurity_governance;personal_shared7agent-memory
4792606.245952026-06-23recent-2026-Apr-JulMEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recoveryhttps://arxiv.org/abs/2606.24595Truesupportingsecurity_privacymodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiency5agent-memory;long-term-memory
4802606.247752026-06-23recent-2026-Apr-JulAre We Ready For An Agent-Native Memory System?https://arxiv.org/abs/2606.24775Truecoreupdate_forgettingmodelretrieval_access;representation_organization;update_forgetting;execution_state;evaluation_diagnosis;security_privacy_trust;systems_efficiency6agent-memory
4812606.251152026-06-23recent-2026-Apr-JulForget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memoryhttps://arxiv.org/abs/2606.25115Truesupportingsecurity_privacymodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui;systems_efficiencyupdate_forgetting;experience_skill_policy;systems_efficiency2agent-memory
4822606.251612026-06-23recent-2026-Apr-JulTRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memoryhttps://arxiv.org/abs/2606.25161Truecoreupdate_forgettingmodelupdate_forgetting;experience_skill_learning;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guiupdate_forgetting;experience_skill_policy;security_governance7agent-memory;long-term-memory
4832606.252062026-06-23recent-2026-Apr-JulRAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memoryhttps://arxiv.org/abs/2606.25206Truecoreexecution_statemodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexecution_multimodal2agent-memory
4842606.266272026-06-25recent-2026-Apr-JulAgents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agentshttps://arxiv.org/abs/2606.26627Falsesupportingsecurity_privacymodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trustbenchmark_diagnosis;security_governance2agent-memory
4852606.267902026-06-25recent-2026-Apr-JulOPID: On-Policy Skill Distillation for Agentic Reinforcement Learninghttps://arxiv.org/abs/2606.26790Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy6procedural-memory
4862606.274992026-06-25recent-2026-Apr-JulDMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injectionhttps://arxiv.org/abs/2606.27499Truecoreexecution_statemodelretrieval_access;execution_state;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guibenchmark_diagnosis;execution_multimodal6agent-memory
4872606.287812026-06-27recent-2026-Apr-JulHyphaeDB: A Living Knowledge Topology for Agent-First Memoryhttps://arxiv.org/abs/2606.28781Truecoreexecution_statemodelretrieval_access;representation_organization;multi_agent_shared;systems_efficiencysystems_efficiency0agent-memory
4882606.289712026-06-27recent-2026-Apr-JulSelf-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Executionhttps://arxiv.org/abs/2606.28971Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy3episodic-memory
4892606.297742026-06-29recent-2026-Apr-JulAnalytic Concept-Centric Memory for Agentic Embodied Manipulationhttps://arxiv.org/abs/2606.29774Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal5agent-memory;memory-evaluation
4902606.297782026-06-29recent-2026-Apr-JulMandol: An Agglomerative Agent Memory System for Long-Term Conversationshttps://arxiv.org/abs/2606.29778Truecoreexecution_statemodelretrieval_access;representation_organization;update_forgetting;evaluation_diagnosis;systems_efficiency4agent-memory
4912606.297882026-06-29recent-2026-Apr-JulMemLeak: Diagnosing Information Leaks in Multimodal Agent Memoryhttps://arxiv.org/abs/2606.29788Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guibenchmark_diagnosis;execution_multimodal;security_governance7agent-memory
4922606.298242026-06-29recent-2026-Apr-JulNeural Procedural Memory: Empowering LLM Agents with Implicit Activation Steeringhttps://arxiv.org/abs/2606.29824Truecoreupdate_forgettingmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy5agent-memory;procedural-memory
4932606.299142026-06-29recent-2026-Apr-JulMemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluationhttps://arxiv.org/abs/2606.29914Truesupportingsecurity_privacymodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis7agent-memory;memory-evaluation
4942606.299612026-06-29recent-2026-Apr-JulDuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillationhttps://arxiv.org/abs/2606.29961Truecoreupdate_forgettingmodelexperience_skill_learning;evaluation_diagnosis;multimodal_embodied_guiexperience_skill_policy;systems_efficiency5agent-memory
4952606.302962026-06-29recent-2026-Apr-JulManimAgent: Self-Evolving Multimodal Agents for Visual Educationhttps://arxiv.org/abs/2606.30296Falsecoreexecution_statemodelretrieval_access;update_forgetting;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy;execution_multimodal6episodic-memory
4962606.305662026-06-29recent-2026-Apr-JulForensic Trajectory Signatures for Agent Memory Poisoning Detectionhttps://arxiv.org/abs/2606.30566Truecoreupdate_forgettingmodelretrieval_access;execution_state;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_guisecurity_governance4agent-memory;long-term-memory
4972606.306392026-06-29recent-2026-Apr-JulSelf-Evolving World Models for LLM Agent Planninghttps://arxiv.org/abs/2606.30639Falsecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosisexperience_skill_policy4episodic-memory
4982606.310462026-06-30recent-2026-Apr-JulOpenLife: Toward Open-World Artificial Life with Autonomous LLM Agentshttps://arxiv.org/abs/2606.31046Falsecoreexperience_learningmodelretrieval_access;representation_organization;experience_skill_learning;evaluation_diagnosis;systems_efficiency2long-term-memory
4992606.316122026-06-30recent-2026-Apr-JulWhat Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving Stateshttps://arxiv.org/abs/2606.31612Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencybenchmark_diagnosis;execution_multimodal3agent-memory
5002607.025792026-06-30recent-2026-Apr-JulWhen Not to Write Memory: Governing False Promotion from Correlated Agent Traceshttps://arxiv.org/abs/2607.02579Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiencyupdate_forgetting;security_governance4agent-memory
5012607.004542026-07-01recent-2026-Apr-JulAgri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generationhttps://arxiv.org/abs/2607.00454Falsecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis;multi_agent_shared;multimodal_embodied_gui;systems_efficiencypersonal_shared6episodic-memory
5022607.010472026-07-01recent-2026-Apr-JulConversable Complexity: Agentic LLM Collectives as Interpretable Substrateshttps://arxiv.org/abs/2607.01047Falsecoreexecution_statemodelretrieval_access;experience_skill_learning;evaluation_diagnosispersonal_shared3long-term-memory
5032607.010712026-07-01recent-2026-Apr-JulMemSyco-Bench: Benchmarking Sycophancy in Agent Memoryhttps://arxiv.org/abs/2607.01071Truecoreexecution_statemodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencybenchmark_diagnosis4agent-memory;memory-evaluation
5042607.015232026-07-01recent-2026-Apr-JulMulti-Head Recurrent Memory Agentshttps://arxiv.org/abs/2607.01523Truecoreupdate_forgettingmodelupdate_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiency7agent-memory
5052607.017092026-07-02recent-2026-Apr-JulCOMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflowshttps://arxiv.org/abs/2607.01709Falsecoreupdate_forgettingmodelretrieval_access;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiencyexperience_skill_policy5agent-memory
5062607.019162026-07-02recent-2026-Apr-JulContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repairhttps://arxiv.org/abs/2607.01916Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;systems_efficiencysystems_efficiency6agent-memory
5072607.019352026-07-02recent-2026-Apr-JulA-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memoryhttps://arxiv.org/abs/2607.01935Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis3agent-memory;long-term-memory
5082607.037262026-07-04recent-2026-Apr-JulSelfMem: Self-Optimizing Memory for AI Agentshttps://arxiv.org/abs/2607.03726Truecoreupdate_forgettingmodelretrieval_access;execution_state;experience_skill_learning;evaluation_diagnosis;multimodal_embodied_gui;systems_efficiency7agent-memory
5092607.040892026-07-05recent-2026-Apr-JulPLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agentshttps://arxiv.org/abs/2607.04089Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;security_privacy_trust;systems_efficiency2agent-memory
5102607.043912026-07-05recent-2026-Apr-JulMemory-Orchestrated Semantic System (MOSS): An Auditable Agentic Memory Architecturehttps://arxiv.org/abs/2607.04391Truecoreupdate_forgettingmodelretrieval_access;representation_organization;systems_efficiency0agent-memory
5112607.050292026-07-06recent-2026-Apr-JulYour Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenseshttps://arxiv.org/abs/2607.05029Truecoreupdate_forgettingmodelretrieval_access;evaluation_diagnosis;security_privacy_trustsecurity_governance6agent-memory;long-term-memory
5122607.055772026-07-06recent-2026-Apr-JulNarrative World Model: Narratology-Grounded Writer Memory for Long-Form Fictionhttps://arxiv.org/abs/2607.05577Truecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis5agent-memory
5132607.065952026-07-06recent-2026-Apr-JulWhen Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agentshttps://arxiv.org/abs/2607.06595Truecoreupdate_forgettingmodelretrieval_access;execution_state;security_privacy_trust;systems_efficiencysecurity_governance4agent-memory;long-term-memory
5142607.061952026-07-07recent-2026-Apr-JulLogicHunter: Testing LLM Agent Frameworks with an Agentic Oraclehttps://arxiv.org/abs/2607.06195Falsecoreupdate_forgettingmodelretrieval_access;representation_organization;evaluation_diagnosis;security_privacy_trust;multimodal_embodied_gui7memory-evaluation
5152607.071082026-07-08recent-2026-Apr-JulSeeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendationhttps://arxiv.org/abs/2607.07108Truecoreupdate_forgettingmodelrepresentation_organization;update_forgetting;experience_skill_learning;multimodal_embodied_guiexecution_multimodal5agent-memory
5162607.080322026-07-09recent-2026-Apr-JulWhat to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agentshttps://arxiv.org/abs/2607.08032Truecoreupdate_forgettingmodelretrieval_access;update_forgetting;evaluation_diagnosis;systems_efficiencyupdate_forgetting5agent-memory
5172607.087162026-07-09recent-2026-Apr-JulRemember When It Matters: Proactive Memory Agent for Long-Horizon Agentshttps://arxiv.org/abs/2607.08716Truecoreupdate_forgettingmodelretrieval_access;representation_organization;execution_state;evaluation_diagnosis;multimodal_embodied_guiexecution_multimodal6agent-memory
Reference in New Issue View Git Blame Copy Permalink