Expand arXiv paper corpus

papers/items/2025-2507-20395-mazeeval-a-benchmark-for-testing-sequential-decision-making-in-language-models.md

@@ -0,0 +1,61 @@
+# Paper: MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models
+
+---
+type: paper
+title: "MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models"
+authors: Hafsteinn Einarsson
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2507.20395
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-07-27
+updated_at: 2025-07-27
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - embodied-agent
+  - reasoning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, embodied-agent, reasoning
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2507.20395

papers/items/2025-2507-20666-mimii-agent-leveraging-llms-with-function-calling-for-relative-evaluation-of-ano.md

@@ -0,0 +1,63 @@
+# Paper: MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection
+
+---
+type: paper
+title: "MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection"
+authors: Harsh Purohit, Tomoya Nishida, Kota Dohi, Takashi Endo, Yohei Kawaguchi
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2507.20666
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-07-28
+updated_at: 2025-07-28
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - eess.AS
+  - cs.AI
+  - cs.LG
+  - cs.SD
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, rag, tool-use
+- arXiv categories: eess.AS, cs.AI, cs.LG, cs.SD
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2507.20666

papers/items/2025-2508-07575-mcptoolbench-a-large-scale-ai-agent-model-context-protocol-mcp-tool-use-benchmar.md

@@ -0,0 +1,60 @@
+# Paper: MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark
+
+---
+type: paper
+title: "MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark"
+authors: Shiqing Fan, Xichen Ding, Liang Zhang, Linjian Mo
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2508.07575
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-08-11
+updated_at: 2025-08-11
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 21
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, tool-use
+- arXiv categories: cs.AI
+- collection score: 21
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2508.07575

papers/items/2025-2508-11027-hell-or-high-water-evaluating-agentic-recovery-from-external-failures.md

@@ -0,0 +1,61 @@
+# Paper: Hell or High Water: Evaluating Agentic Recovery from External Failures
+
+---
+type: paper
+title: "Hell or High Water: Evaluating Agentic Recovery from External Failures"
+authors: Andrew Wang, Sophia Hager, Adi Asija, Daniel Khashabi, Nicholas Andrews
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2508.11027
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-08-14
+updated_at: 2025-08-14
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - planning
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, planning, tool-use, workflow-agent
+- arXiv categories: cs.CL
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2508.11027

papers/items/2025-2508-12685-toolace-mt-non-autoregressive-generation-for-agentic-multi-turn-interaction.md

@@ -0,0 +1,61 @@
+# Paper: ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
+
+---
+type: paper
+title: "ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction"
+authors: Xingshan Zeng, Weiwen Liu, Lingzhi Wang, Liangyou Li, Fei Mi, Yasheng Wang, Lifeng Shang, Xin Jiang, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2508.12685
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-08-18
+updated_at: 2026-02-13
+status: queued
+relevance: high
+topics:
+  - tool-use
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: tool-use, world-model
+- arXiv categories: cs.CL, cs.AI, cs.LG
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2508.12685

papers/items/2025-2508-17094-powerchain-a-verifiable-agentic-ai-system-for-automating-distribution-grid-analy.md

@@ -0,0 +1,63 @@
+# Paper: PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses
+
+---
+type: paper
+title: "PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses"
+authors: Emmanuel O. Badmus, Peng Sang, Dimitrios Stamoulis, Amritanshu Pandey
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2508.17094
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-08-23
+updated_at: 2025-10-21
+status: queued
+relevance: high
+topics:
+  - planning
+  - rag
+  - reasoning
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - eess.SY
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: planning, rag, reasoning, tool-use, workflow-agent
+- arXiv categories: cs.AI, eess.SY
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2508.17094

papers/items/2025-2509-02444-appcopilot-toward-general-accurate-long-horizon-and-efficient-mobile-agent.md

@@ -0,0 +1,66 @@
+# Paper: AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
+
+---
+type: paper
+title: "AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent"
+authors: Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Chen Qian
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.02444
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-02
+updated_at: 2025-10-17
+status: queued
+relevance: high
+topics:
+  - computer-use
+  - memory
+  - multi-agent
+  - planning
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+  - cs.CV
+  - cs.HC
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: computer-use, memory, multi-agent, planning, reasoning, tool-use
+- arXiv categories: cs.AI, cs.CL, cs.CV, cs.HC
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.02444

papers/items/2025-2509-02494-gridmind-llms-powered-agents-for-power-system-analysis-and-operations.md

@@ -0,0 +1,60 @@
+# Paper: GridMind: LLMs-Powered Agents for Power System Analysis and Operations
+
+---
+type: paper
+title: "GridMind: LLMs-Powered Agents for Power System Analysis and Operations"
+authors: Hongwei Jin, Kibaek Kim, Jonghwan Kwon
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.02494
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-02
+updated_at: 2025-09-02
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - multi-agent
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, multi-agent, workflow-agent
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.02494

papers/items/2025-2509-08863-geojson-agents-a-multi-agent-llm-architecture-for-geospatial-analysis-function-c.md

@@ -0,0 +1,62 @@
+# Paper: GeoJSON Agents:A Multi-Agent LLM Architecture for Geospatial Analysis-Function Calling vs Code Generation
+
+---
+type: paper
+title: "GeoJSON Agents:A Multi-Agent LLM Architecture for Geospatial Analysis-Function Calling vs Code Generation"
+authors: Qianqian Luo, Qingming Lin, Liuchang Xu, Sensen Wu, Ruichen Mao, Chao Wang, Hailin Feng, Bo Huang, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.08863
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-10
+updated_at: 2025-12-03
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - multi-agent
+  - planning
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, multi-agent, planning, tool-use, workflow-agent
+- arXiv categories: cs.SE
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.08863

papers/items/2025-2509-10769-agentarch-a-comprehensive-benchmark-to-evaluate-agent-architectures-in-enterpris.md

@@ -0,0 +1,64 @@
+# Paper: AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise
+
+---
+type: paper
+title: "AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise"
+authors: Tara Bogavelli, Roshnee Sharma, Hari Subramani
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.10769
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-13
+updated_at: 2026-01-06
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - memory
+  - multi-agent
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, memory, multi-agent, tool-use, workflow-agent
+- arXiv categories: cs.AI, cs.CL, cs.MA
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.10769

papers/items/2025-2509-13311-towards-general-agentic-intelligence-via-environment-scaling.md

@@ -0,0 +1,59 @@
+# Paper: Towards General Agentic Intelligence via Environment Scaling
+
+---
+type: paper
+title: Towards General Agentic Intelligence via Environment Scaling
+authors: Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.13311
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-16
+updated_at: 2025-09-16
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, tool-use
+- arXiv categories: cs.CL
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.13311

papers/items/2025-2509-14477-ticket-bench-a-kickoff-for-multilingual-and-regionalized-agent-evaluation.md

@@ -0,0 +1,60 @@
+# Paper: Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation
+
+---
+type: paper
+title: "Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation"
+authors: Thales Sales Almeida, João Guilherme Alves Santos, Thiago Laitz, Giovana Kerche Bonás
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.14477
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-17
+updated_at: 2025-09-17
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - reasoning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, reasoning
+- arXiv categories: cs.CL
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.14477

papers/items/2025-2509-20998-core-full-path-evaluation-of-llm-agents-beyond-final-state.md

@@ -0,0 +1,61 @@
+# Paper: CORE: Full-Path Evaluation of LLM Agents Beyond Final State
+
+---
+type: paper
+title: "CORE: Full-Path Evaluation of LLM Agents Beyond Final State"
+authors: Panagiotis Michelakis, Yiannis Hadjiyiannis, Dimitrios Stamoulis
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.20998
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-25
+updated_at: 2025-09-25
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - tool-use
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 20
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, tool-use, world-model
+- arXiv categories: cs.AI
+- collection score: 20
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.20998

papers/items/2025-2509-26553-towards-reliable-benchmarking-a-contamination-free-controllable-evaluation-frame.md

@@ -0,0 +1,61 @@
+# Paper: Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling
+
+---
+type: paper
+title: "Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling"
+authors: Seiji Maekawa, Jackson Hassell, Pouya Pezeshkpour, Tom Mitchell, Estevam Hruschka
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2509.26553
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-09-30
+updated_at: 2026-02-06
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.PL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, reasoning, tool-use
+- arXiv categories: cs.CL, cs.PL
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2509.26553

papers/items/2025-2510-03847-small-language-models-for-agentic-systems-a-survey-of-architectures-capabilities.md

@@ -0,0 +1,65 @@
+# Paper: Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
+
+---
+type: paper
+title: "Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs"
+authors: Raghav Sharma, Manan Mehta
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.03847
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-04
+updated_at: 2025-10-04
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - computer-use
+  - planning
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 19
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, coding-agent, computer-use, planning, rag, reasoning, tool-use
+- arXiv categories: cs.AI, cs.LG
+- collection score: 19
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.03847

papers/items/2025-2510-04206-agentrl-scaling-agentic-reinforcement-learning-with-a-multi-turn-multi-task-fram.md

@@ -0,0 +1,59 @@
+# Paper: AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
+
+---
+type: paper
+title: "AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework"
+authors: Hanchen Zhang, Xiao Liu, Bowen Lv, Xueqiao Sun, Bohao Jing, Iat Long Iong, Zhenyu Hou, Zehan Qi, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.04206
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-05
+updated_at: 2025-10-05
+status: queued
+relevance: high
+topics:
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.04206

papers/items/2025-2510-14548-llm-agents-beyond-utility-an-open-ended-perspective.md

@@ -0,0 +1,61 @@
+# Paper: LLM Agents Beyond Utility: An Open-Ended Perspective
+
+---
+type: paper
+title: "LLM Agents Beyond Utility: An Open-Ended Perspective"
+authors: Asen Nachkov, Xi Wang, Luc Van Gool
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.14548
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-16
+updated_at: 2025-10-16
+status: queued
+relevance: high
+topics:
+  - memory
+  - planning
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: memory, planning, reasoning, tool-use
+- arXiv categories: cs.AI
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.14548

papers/items/2025-2510-18586-tokencake-a-kv-cache-centric-serving-framework-for-llm-based-multi-agent-applica.md

@@ -0,0 +1,61 @@
+# Paper: TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
+
+---
+type: paper
+title: "TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications"
+authors: Zhuohang Bian, Feiyang Wu, Zhuoran Li, Teng Ma, Youwei Zhuo
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.18586
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-21
+updated_at: 2026-05-20
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - memory
+  - multi-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.DC
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, memory, multi-agent
+- arXiv categories: cs.DC
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.18586

papers/items/2025-2510-21524-eu-agent-bench-measuring-illegal-behavior-of-llm-agents-under-eu-law.md

@@ -0,0 +1,61 @@
+# Paper: EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
+
+---
+type: paper
+title: "EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law"
+authors: Ilija Lichkovski, Alexander Müller, Mariam Ibrahim, Tiwai Mhundwa
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.21524
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-24
+updated_at: 2025-10-24
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.21524

papers/items/2025-2510-22768-seeing-is-believing-evaluating-vision-language-model-susceptibility-in-agent-to-.md

@@ -0,0 +1,62 @@
+# Paper: Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion
+
+---
+type: paper
+title: Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion
+authors: Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit, Kung-Hsiang Huang, Jiaxin Zhang, Nanyun Peng, Chien-Sheng Wu
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.22768
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-26
+updated_at: 2026-06-02
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - multi-agent
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, multi-agent, rag, tool-use
+- arXiv categories: cs.CL
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.22768

papers/items/2025-2510-24645-funreason-mt-technical-report-advanced-data-synthesis-solution-for-real-world-mu.md

@@ -0,0 +1,61 @@
+# Paper: FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
+
+---
+type: paper
+title: "FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use"
+authors: Zengzhuang Xu, Bingguang Hao, Zechuan Wang, Yuntao Wen, Xinyi Xu, Yang Liu, Long Chen, Dong Wang, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.24645
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-28
+updated_at: 2025-11-16
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - multi-agent
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, multi-agent, tool-use
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.24645

papers/items/2025-2510-26167-toolrm-towards-agentic-tool-use-reward-modeling.md

@@ -0,0 +1,60 @@
+# Paper: ToolRM: Towards Agentic Tool-Use Reward Modeling
+
+---
+type: paper
+title: "ToolRM: Towards Agentic Tool-Use Reward Modeling"
+authors: Renhao Li, Jianhong Tu, Yang Su, Yantao Liu, Fei Huang, Hamid Alinejad-Rokny, Derek F. Wong, Junyang Lin, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2510.26167
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-10-30
+updated_at: 2026-01-13
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, tool-use
+- arXiv categories: cs.AI, cs.CL
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2510.26167

papers/items/2025-2511-04847-test-time-adaptation-for-llm-agents-via-environment-interaction.md

@@ -0,0 +1,63 @@
+# Paper: Test-Time Adaptation for LLM Agents via Environment Interaction
+
+---
+type: paper
+title: Test-Time Adaptation for LLM Agents via Environment Interaction
+authors: Arthur Chen, Zuxin Liu, Jianguo Zhang, Akshara Prabhakar, Zhiwei Liu, Shelby Heinecke, Silvio Savarese, Victor Zhong, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2511.04847
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-11-06
+updated_at: 2026-02-22
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - embodied-agent
+  - rag
+  - tool-use
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, embodied-agent, rag, tool-use, world-model
+- arXiv categories: cs.LG
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2511.04847

papers/items/2025-2511-11169-refine-and-align-confidence-calibration-through-multi-agent-interaction-in-vqa.md

@@ -0,0 +1,63 @@
+# Paper: Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
+
+---
+type: paper
+title: "Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA"
+authors: Ayush Pandey, Jai Bardhan, Ishita Jain, Ramya S Hebbalaguppe, Rohan Raju Dhanakshirur, Lovekesh Vig
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2511.11169
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-11-14
+updated_at: 2025-11-14
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - embodied-agent
+  - multi-agent
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CV
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, embodied-agent, multi-agent, tool-use
+- arXiv categories: cs.CV, cs.AI, cs.LG
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2511.11169

papers/items/2025-2511-15203-taxonomy-evaluation-and-exploitation-of-ipi-centric-llm-agent-defense-frameworks.md

@@ -0,0 +1,62 @@
+# Paper: Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
+
+---
+type: paper
+title: Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
+authors: Zimo Ji, Xunguang Wang, Zongjie Li, Pingchuan Ma, Yudong Gao, Daoyuan Wu, Xincheng Yan, Tian Tian, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2511.15203
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-11-19
+updated_at: 2025-11-19
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, rag, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2511.15203

papers/items/2025-2511-22138-tinyllm-evaluation-and-optimization-of-small-language-models-for-agentic-tasks-o.md

@@ -0,0 +1,60 @@
+# Paper: TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
+
+---
+type: paper
+title: "TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices"
+authors: Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta, Khalil Shujaee, Roy George
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2511.22138
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-11-27
+updated_at: 2025-11-27
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, tool-use
+- arXiv categories: cs.LG
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2511.22138

papers/items/2025-2512-02605-iact-a-self-organizing-recursive-model-for-general-ai-agents-a-technical-white-p.md

@@ -0,0 +1,65 @@
+# Paper: IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai
+
+---
+type: paper
+title: "IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai"
+authors: Pengju Lu
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2512.02605
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-12-02
+updated_at: 2025-12-02
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - memory
+  - rag
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.MA
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, memory, rag, tool-use, workflow-agent
+- arXiv categories: cs.AI, cs.MA, cs.SE
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2512.02605

papers/items/2025-2512-11682-medai-evaluating-txagent-s-therapeutic-agentic-reasoning-in-the-neurips-cure-ben.md

@@ -0,0 +1,65 @@
+# Paper: MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition
+
+---
+type: paper
+title: "MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition"
+authors: Tim Cofala, Christian Kalfar, Jingge Xiao, Johanna Schrader, Michelle Tang, Wolfgang Nejdl
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2512.11682
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-12-12
+updated_at: 2026-06-15
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - computer-use
+  - planning
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, computer-use, planning, rag, reasoning, tool-use
+- arXiv categories: cs.AI, cs.LG
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2512.11682

papers/items/2025-2512-23611-close-the-loop-synthesizing-infinite-tool-use-data-via-multi-agent-role-playing.md

@@ -0,0 +1,62 @@
+# Paper: Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing
+
+---
+type: paper
+title: "Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing"
+authors: Yuwen Li, Wei Zhang, Zelong Huang, Mason Yang, Jiajun Wu, Shawn Guo, Huahao Hu, Lingyi Sun, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2512.23611
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-12-29
+updated_at: 2025-12-29
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - multi-agent
+  - rag
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, multi-agent, rag, tool-use, workflow-agent
+- arXiv categories: cs.CL
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2512.23611

papers/items/2025-2512-23647-nested-browser-use-learning-for-agentic-information-seeking.md

@@ -0,0 +1,65 @@
+# Paper: Nested Browser-Use Learning for Agentic Information Seeking
+
+---
+type: paper
+title: Nested Browser-Use Learning for Agentic Information Seeking
+authors: Baixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li, Zhongwang Zhang, Huifeng Yin, Zhengwei Tao, Liwen Zhang, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2512.23647
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-12-29
+updated_at: 2025-12-29
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.AI
+  - cs.IR
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, rag, reasoning, tool-use
+- arXiv categories: cs.CL, cs.AI, cs.IR, cs.MA
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2512.23647

papers/items/2025-2512-23747-state-of-the-art-small-language-coder-model-mify-coder.md

@@ -0,0 +1,64 @@
+# Paper: State-of-the-art Small Language Coder Model: Mify-Coder
+
+---
+type: paper
+title: "State-of-the-art Small Language Coder Model: Mify-Coder"
+authors: Abhinav Parmar, Abhisek Panigrahi, Abhishek Kumar Dwivedi, Abhishek Bhattacharya, Adarsh Ramachandra, Aditya Choudhary, Aditya Garg, Aditya Raj, et al.
+year: 2025
+venue: arXiv
+url: https://arxiv.org/abs/2512.23747
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2025-12-26
+updated_at: 2025-12-26
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - coding-agent
+  - computer-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, coding-agent, computer-use, workflow-agent
+- arXiv categories: cs.SE, cs.AI, cs.CL
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2512.23747

papers/items/2026-2601-00268-beyond-perfect-apis-a-comprehensive-evaluation-of-llm-agents-under-real-world-ap.md

@@ -0,0 +1,60 @@
+# Paper: Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
+
+---
+type: paper
+title: "Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity"
+authors: Doyoung Kim, Zhiwei Ren, Jie Hao, Zhongkai Sun, Lichao Wang, Xiyao Ma, Zack Ye, Xu Han, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.00268
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-01
+updated_at: 2026-01-01
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, tool-use
+- arXiv categories: cs.CL, cs.AI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.00268

papers/items/2026-2601-05467-stelp-secure-transpilation-and-execution-of-llm-generated-programs.md

@@ -0,0 +1,64 @@
+# Paper: STELP: Secure Transpilation and Execution of LLM-Generated Programs
+
+---
+type: paper
+title: "STELP: Secure Transpilation and Execution of LLM-Generated Programs"
+authors: Swapnil Shinde, Sahil Wadhwa, Andy Luo, Akshay Gupta, Mohammad Shahed Sorower
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.05467
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-09
+updated_at: 2026-01-15
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - multi-agent
+  - planning
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, multi-agent, planning, reasoning, tool-use
+- arXiv categories: cs.SE, cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.05467

papers/items/2026-2601-06007-don-t-break-the-cache-an-evaluation-of-prompt-caching-for-long-horizon-agentic-t.md

@@ -0,0 +1,61 @@
+# Paper: Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
+
+---
+type: paper
+title: "Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks"
+authors: Elias Lumer, Faheem Nizar, Akshaya Jangiti, Kevin Frank, Anmol Gulati, Mandar Phadate, Vamse Kumar Subbiah
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.06007
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-09
+updated_at: 2026-01-31
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - planning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, planning, tool-use
+- arXiv categories: cs.CL
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.06007

papers/items/2026-2601-06606-cedar-context-engineering-for-agentic-data-science.md

@@ -0,0 +1,60 @@
+# Paper: CEDAR: Context Engineering for Agentic Data Science
+
+---
+type: paper
+title: "CEDAR: Context Engineering for Agentic Data Science"
+authors: Rishiraj Saha Roy, Chris Hinze, Luzian Hahn, Fabian Kuech
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.06606
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-10
+updated_at: 2026-04-22
+status: queued
+relevance: high
+topics:
+  - planning
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: planning, workflow-agent
+- arXiv categories: cs.LG, cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.06606

papers/items/2026-2601-12988-paperguide-making-small-language-model-paper-reading-agents-more-efficient.md

@@ -0,0 +1,62 @@
+# Paper: PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient
+
+---
+type: paper
+title: "PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient"
+authors: Zijian Wang, Tiancheng Huang, Hanqi Li, Da Ma, Lu Chen, Kai Yu
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.12988
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-19
+updated_at: 2026-01-19
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - planning
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, planning, reasoning, tool-use
+- arXiv categories: cs.LG
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.12988

papers/items/2026-2601-14652-mas-orchestra-understanding-and-improving-multi-agent-reasoning-through-holistic.md

@@ -0,0 +1,63 @@
+# Paper: MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
+
+---
+type: paper
+title: "MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks"
+authors: Zixuan Ke, Yifei Ming, Austin Xu, Ryan Chin, Xuan-Phi Nguyen, Prathyusha Jwalapuram, Jiayu Wang, Semih Yavuz, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2601.14652
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-01-21
+updated_at: 2026-05-21
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - multi-agent
+  - reasoning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use, multi-agent, reasoning
+- arXiv categories: cs.AI, cs.CL, cs.MA
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2601.14652

papers/items/2026-2602-03117-agentdyn-are-your-agent-security-defenses-deployable-in-real-world-dynamic-envir.md

@@ -0,0 +1,61 @@
+# Paper: AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
+
+---
+type: paper
+title: "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"
+authors: Hao Li, Ruoyao Wen, Shanghao Shi, Ning Zhang, Yevgeniy Vorobeychik, Chaowei Xiao
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.03117
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-03
+updated_at: 2026-05-07
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - planning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, planning, tool-use
+- arXiv categories: cs.CR
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.03117

papers/items/2026-2602-03224-tame-a-trustworthy-test-time-evolution-of-agent-memory-with-systematic-benchmark.md

@@ -0,0 +1,63 @@
+# Paper: TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
+
+---
+type: paper
+title: "TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking"
+authors: Yu Cheng, Yongkang Hu, Jiuan Zhou, Yushuo Zhang, Yihang Chen, Huichi Zhou, Mingang Chen, Zhizhong Zhang, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.03224
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-03
+updated_at: 2026-06-06
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - computer-use
+  - memory
+  - reasoning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, computer-use, memory, reasoning
+- arXiv categories: cs.AI, cs.LG
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.03224

papers/items/2026-2602-03786-aorchestra-automating-sub-agent-creation-for-agentic-orchestration.md

@@ -0,0 +1,63 @@
+# Paper: AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
+
+---
+type: paper
+title: "AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration"
+authors: Jianhao Ruan, Zhihao Xu, Yiran Peng, Fashen Ren, Zhaoyang Yu, Xinbing Liang, Jinyu Xiang, Yongru Chen, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.03786
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-03
+updated_at: 2026-02-07
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - planning
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, coding-agent, planning, tool-use, workflow-agent
+- arXiv categories: cs.AI, cs.CL
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.03786

papers/items/2026-2602-05115-socialveil-probing-social-intelligence-of-language-agents-under-communication-ba.md

@@ -0,0 +1,61 @@
+# Paper: SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers
+
+---
+type: paper
+title: "SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers"
+authors: Keyang Xuan, Pengda Wang, Chongrui Ye, Haofei Yu, Tal August, Jiaxuan You
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.05115
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-04
+updated_at: 2026-02-04
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, rag, tool-use
+- arXiv categories: cs.AI, cs.CL
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.05115

papers/items/2026-2602-05302-piearena-ranking-and-profiling-language-agents-in-realistic-negotiation-scenario.md

@@ -0,0 +1,61 @@
+# Paper: PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios
+
+---
+type: paper
+title: "PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios"
+authors: Chris Zhu, Sasha Cui, Will Sanok Dufallo, Runzhi Jin, Zhen Xu, Linjun Zhang, Daylian Cain
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.05302
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-05
+updated_at: 2026-06-01
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - multi-agent
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, multi-agent, reasoning, tool-use
+- arXiv categories: cs.AI
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.05302

papers/items/2026-2602-05386-spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchica.md

@@ -0,0 +1,62 @@
+# Paper: Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
+
+---
+type: paper
+title: "Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening"
+authors: Zhenxiong Yu, Zhi Yang, Zhiheng Jin, Shuhe Wang, Heng Zhang, Yanlin Fei, Lingfeng Zeng, Fangqi Lou, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.05386
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-05
+updated_at: 2026-02-06
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, reasoning, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.05386

papers/items/2026-2602-07391-naamse-framework-for-evolutionary-security-evaluation-of-agents.md

@@ -0,0 +1,60 @@
+# Paper: NAAMSE: Framework for Evolutionary Security Evaluation of Agents
+
+---
+type: paper
+title: "NAAMSE: Framework for Evolutionary Security Evaluation of Agents"
+authors: Kunal Pai, Parth Shah, Harshil Patel
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.07391
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-07
+updated_at: 2026-03-08
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety
+- arXiv categories: cs.AI, cs.MA
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.07391

papers/items/2026-2602-07652-agent-fence-mapping-security-vulnerabilities-across-deep-research-agents.md

@@ -0,0 +1,64 @@
+# Paper: Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
+
+---
+type: paper
+title: "Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents"
+authors: Sai Puppala, Ismail Hossain, Md Jahangir Alam, Yoonpyo Lee, Jay Yoo, Tanzim Ahad, Syed Bahauddin Alam, Sajedul Talukder
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.07652
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-07
+updated_at: 2026-02-07
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - memory
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, memory, planning, rag, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.07652

papers/items/2026-2602-07962-loca-bench-benchmarking-language-agents-under-controllable-and-extreme-context-g.md

@@ -0,0 +1,61 @@
+# Paper: LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
+
+---
+type: paper
+title: "LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth"
+authors: Weihao Zeng, Yuzhen Huang, Junxian He
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.07962
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-08
+updated_at: 2026-02-08
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, planning, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.07962

papers/items/2026-2602-08082-spectral-guardrails-for-agents-in-the-wild-detecting-tool-use-hallucinations-via.md

@@ -0,0 +1,62 @@
+# Paper: Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology
+
+---
+type: paper
+title: "Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology"
+authors: Valentin Noël
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.08082
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-08
+updated_at: 2026-02-08
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+  - cs.AI
+  - eess.SP
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, tool-use
+- arXiv categories: cs.LG, cs.AI, eess.SP
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.08082

papers/items/2026-2602-08412-from-assistant-to-double-agent-formalizing-and-benchmarking-attacks-on-openclaw-.md

@@ -0,0 +1,63 @@
+# Paper: From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
+
+---
+type: paper
+title: "From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent"
+authors: Yuhang Wang, Feiming Xu, Zheng Lin, Guangyu He, Yuzhe Huang, Haichang Gao, Zhenxing Niu, Shiguo Lian, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.08412
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-09
+updated_at: 2026-02-11
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - memory
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 21
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, memory, planning, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 21
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.08412

papers/items/2026-2602-10133-agenttrace-a-structured-logging-framework-for-agent-system-observability.md

@@ -0,0 +1,62 @@
+# Paper: AgentTrace: A Structured Logging Framework for Agent System Observability
+
+---
+type: paper
+title: "AgentTrace: A Structured Logging Framework for Agent System Observability"
+authors: Adam AlSayyad, Kelvin Yuxiang Huang, Richik Pal
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.10133
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-07
+updated_at: 2026-02-07
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, reasoning, tool-use
+- arXiv categories: cs.SE, cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.10133

papers/items/2026-2602-11749-air-improving-agent-safety-through-incident-response.md

@@ -0,0 +1,61 @@
+# Paper: AIR: Improving Agent Safety through Incident Response
+
+---
+type: paper
+title: "AIR: Improving Agent Safety through Incident Response"
+authors: Zibo Xiao, Jun Sun, Junjie Chen
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.11749
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-12
+updated_at: 2026-06-20
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - computer-use
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, computer-use, tool-use
+- arXiv categories: cs.AI
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.11749

papers/items/2026-2602-13379-unsafer-in-many-turns-benchmarking-and-defending-multi-turn-safety-risks-in-tool.md

@@ -0,0 +1,65 @@
+# Paper: Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
+
+---
+type: paper
+title: "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"
+authors: Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Bo Li, Dawn Song, Xue Lin, Weiyan Shi
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.13379
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-13
+updated_at: 2026-06-10
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+  - cs.CL
+  - cs.LG
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, rag, tool-use
+- arXiv categories: cs.CR, cs.AI, cs.CL, cs.LG, cs.SE
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.13379

papers/items/2026-2602-13530-remem-reasoning-with-episodic-memory-in-language-agent.md

@@ -0,0 +1,62 @@
+# Paper: REMem: Reasoning with Episodic Memory in Language Agent
+
+---
+type: paper
+title: "REMem: Reasoning with Episodic Memory in Language Agent"
+authors: Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao, Bernal Jiménez Gutiérrez, Weijian Qi, Kamalika Das, Huan Sun, Yu Su
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.13530
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-13
+updated_at: 2026-02-28
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - memory
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 19
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, memory, rag, reasoning, tool-use
+- arXiv categories: cs.AI
+- collection score: 19
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.13530

papers/items/2026-2602-13665-hyfunc-accelerating-llm-based-function-calls-for-agentic-ai-through-hybrid-model.md

@@ -0,0 +1,59 @@
+# Paper: HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating
+
+---
+type: paper
+title: "HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating"
+authors: Weibin Liao, Jian-guang Lou, Haoyi Xiong
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.13665
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-14
+updated_at: 2026-02-14
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, computer-use
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.13665

papers/items/2026-2602-14234-redsearcher-a-scalable-and-cost-efficient-framework-for-long-horizon-search-agen.md

@@ -0,0 +1,62 @@
+# Paper: REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
+
+---
+type: paper
+title: "REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents"
+authors: Zheng Chu, Xiao Wang, Jack Hong, Huiming Fan, Yuqi Huang, Yue Yang, Guohai Xu, Chenxiao Zhao, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.14234
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-15
+updated_at: 2026-02-15
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, planning, rag, tool-use
+- arXiv categories: cs.AI, cs.CL
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.14234

papers/items/2026-2602-14281-mcpshield-a-security-cognition-layer-for-adaptive-trust-calibration-in-model-con.md

@@ -0,0 +1,62 @@
+# Paper: MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
+
+---
+type: paper
+title: "MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents"
+authors: Zhenhong Zhou, Yuanhe Zhang, Hongwei Cai, Moayad Aloqaily, Ouns Bouachir, Linsey Pang, Prakhar Mehrotra, Kun Wang, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.14281
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-15
+updated_at: 2026-02-24
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - computer-use
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, computer-use, reasoning, tool-use
+- arXiv categories: cs.CR, cs.CL
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.14281

papers/items/2026-2602-16931-narrow-fine-tuning-erodes-safety-alignment-in-vision-language-agents.md

@@ -0,0 +1,59 @@
+# Paper: Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
+
+---
+type: paper
+title: Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
+authors: Idhant Gulati, Shivam Raval
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.16931
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-18
+updated_at: 2026-03-15
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, agent-safety
+- arXiv categories: cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.16931

papers/items/2026-2602-18456-beyond-single-channel-agentic-benchmarking.md

@@ -0,0 +1,61 @@
+# Paper: Beyond single-channel agentic benchmarking
+
+---
+type: paper
+title: Beyond single-channel agentic benchmarking
+authors: Nelu D. Radpour
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.18456
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-05
+updated_at: 2026-02-05
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CY
+  - cs.AI
+  - cs.HC
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety
+- arXiv categories: cs.CY, cs.AI, cs.HC
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.18456

papers/items/2026-2602-19008-capable-but-unreliable-canonical-path-deviation-as-a-causal-mechanism-of-agent-f.md

@@ -0,0 +1,62 @@
+# Paper: Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
+
+---
+type: paper
+title: "Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks"
+authors: Wilson Y. Lee
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.19008
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-22
+updated_at: 2026-02-22
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - planning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, computer-use, planning, tool-use
+- arXiv categories: cs.CL, cs.LG
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.19008

papers/items/2026-2602-21127-are-you-sure-an-empirical-study-of-human-perception-vulnerability-in-llm-driven-.md

@@ -0,0 +1,63 @@
+# Paper: "Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems
+
+---
+type: paper
+title: "\"Are You Sure?\": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems"
+authors: Xinfeng Li, Shenyu Dai, Kelong Zheng, Yue Xiao, Gelei Deng, Wei Dong, Xiaofeng Wang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.21127
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-24
+updated_at: 2026-02-24
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.HC
+  - cs.AI
+  - cs.CR
+  - cs.SI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, tool-use, workflow-agent
+- arXiv categories: cs.HC, cs.AI, cs.CR, cs.SI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.21127

papers/items/2026-2602-23320-parammem-augmenting-language-agents-with-parametric-reflective-memory.md

@@ -0,0 +1,61 @@
+# Paper: ParamMem: Augmenting Language Agents with Parametric Reflective Memory
+
+---
+type: paper
+title: "ParamMem: Augmenting Language Agents with Parametric Reflective Memory"
+authors: Tianjun Yao, Yongqiang Chen, Yujia Zheng, Pan Li, Zhiqiang Shen, Kun Zhang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2602.23320
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-26
+updated_at: 2026-02-27
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - memory
+  - reasoning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, memory, reasoning
+- arXiv categories: cs.LG, cs.MA
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2602.23320

papers/items/2026-2603-00131-thought-virus-viral-misalignment-via-subliminal-prompting-in-multi-agent-systems.md

@@ -0,0 +1,61 @@
+# Paper: Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems
+
+---
+type: paper
+title: "Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems"
+authors: Moritz Weckbecker, Jonas Müller, Ben Hagag, Michael Mulet
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.00131
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-23
+updated_at: 2026-02-23
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - multi-agent
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.MA
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, multi-agent, tool-use
+- arXiv categories: cs.MA, cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.00131

papers/items/2026-2603-00623-tracesir-a-multi-agent-framework-for-structured-analysis-and-reporting-of-agenti.md

@@ -0,0 +1,63 @@
+# Paper: TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
+
+---
+type: paper
+title: "TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces"
+authors: Shu-Xun Yang, Cunxiang Wang, Haoke Zhang, Wenbo Yu, Lindong Wu, Jiayi Gui, Dayong Yang, Yukuo Cen, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.00623
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-28
+updated_at: 2026-02-28
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - multi-agent
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 19
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, coding-agent, multi-agent, reasoning, tool-use
+- arXiv categories: cs.AI, cs.CL
+- collection score: 19
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.00623

papers/items/2026-2603-00801-the-synthetic-web-adversarially-curated-mini-internets-for-diagnosing-epistemic-.md

@@ -0,0 +1,62 @@
+# Paper: The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents
+
+---
+type: paper
+title: "The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents"
+authors: Shrey Shah, Levent Ozgur
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.00801
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-28
+updated_at: 2026-02-28
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - embodied-agent
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.IR
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, embodied-agent, rag, tool-use
+- arXiv categories: cs.AI, cs.IR
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.00801

papers/items/2026-2603-01438-enhancing-persona-following-at-decoding-time-via-dynamic-importance-estimation-f.md

@@ -0,0 +1,64 @@
+# Paper: Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
+
+---
+type: paper
+title: Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
+authors: Yuxin Liu, Mingye Zhu, Siyuan Liu, Bo Hu, Lei Zhang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.01438
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-02
+updated_at: 2026-03-02
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - coding-agent
+  - computer-use
+  - planning
+  - rag
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-safety, coding-agent, computer-use, planning, rag, world-model
+- arXiv categories: cs.CL, cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.01438

papers/items/2026-2603-01712-ft-dojo-towards-autonomous-llm-fine-tuning-with-language-agents.md

@@ -0,0 +1,61 @@
+# Paper: FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
+
+---
+type: paper
+title: "FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents"
+authors: Qizheng Li, Yifei Zhang, Xiao Yang, Xu Yang, Zhuo Wang, Weiqing Liu, Jiang Bian
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.01712
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-02
+updated_at: 2026-05-20
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - planning
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, coding-agent, planning
+- arXiv categories: cs.AI, cs.LG
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.01712

papers/items/2026-2603-02711-a-natural-language-agentic-approach-to-study-affective-polarization.md

@@ -0,0 +1,60 @@
+# Paper: A Natural Language Agentic Approach to Study Affective Polarization
+
+---
+type: paper
+title: A Natural Language Agentic Approach to Study Affective Polarization
+authors: Stephanie Anneris Malvicini, Ewelina Gajewska, Arda Derbent, Katarzyna Budzynska, Jarosław A. Chudziak, Maria Vanina Martinez
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.02711
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-03
+updated_at: 2026-03-03
+status: queued
+relevance: high
+topics:
+  - multi-agent
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: multi-agent, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.02711

papers/items/2026-2603-03515-the-controllability-trap-a-governance-framework-for-military-ai-agents.md

@@ -0,0 +1,63 @@
+# Paper: The Controllability Trap: A Governance Framework for Military AI Agents
+
+---
+type: paper
+title: "The Controllability Trap: A Governance Framework for Military AI Agents"
+authors: Subramanyam Sahoo
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.03515
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-03
+updated_at: 2026-03-03
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - planning
+  - tool-use
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CY
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, planning, tool-use, world-model
+- arXiv categories: cs.CY, cs.AI
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.03515

papers/items/2026-2603-03680-mage-meta-reinforcement-learning-for-language-agents-toward-strategic-exploratio.md

@@ -0,0 +1,61 @@
+# Paper: MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation
+
+---
+type: paper
+title: "MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation"
+authors: Lu Yang, Zelai Xu, Minyang Xie, Jiaxuan Gao, Zhao Shok, Yu Wang, Yi Wu
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.03680
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-04
+updated_at: 2026-03-04
+status: queued
+relevance: high
+topics:
+  - memory
+  - multi-agent
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: memory, multi-agent, reasoning, tool-use
+- arXiv categories: cs.AI
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.03680

papers/items/2026-2603-05553-eigendata-a-self-evolving-multi-agent-platform-for-function-calling-data-synthes.md

@@ -0,0 +1,63 @@
+# Paper: EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair
+
+---
+type: paper
+title: "EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair"
+authors: Jiaao Chen, Jingyuan Qi, Mingye Gao, Wei-Chen Wang, Hanrui Wang, Di Jin
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.05553
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-05
+updated_at: 2026-03-05
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - multi-agent
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, coding-agent, multi-agent, tool-use
+- arXiv categories: cs.SE, cs.AI, cs.CL
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.05553

papers/items/2026-2603-05578-tool-genesis-a-task-driven-tool-creation-benchmark-for-self-evolving-language-ag.md

@@ -0,0 +1,61 @@
+# Paper: Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
+
+---
+type: paper
+title: "Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent"
+authors: Bowei Xia, Mengkang Hu, Shijian Wang, Jiarui Jin, Wenxiang Jiao, Yuan Lu, Kexin Li, Ping Luo
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.05578
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-05
+updated_at: 2026-03-05
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, computer-use, tool-use
+- arXiv categories: cs.SE, cs.AI
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.05578

papers/items/2026-2603-07496-from-thinker-to-society-security-in-hierarchical-autonomy-evolution-of-ai-agents.md

@@ -0,0 +1,64 @@
+# Paper: From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
+
+---
+type: paper
+title: "From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents"
+authors: Xiaolei Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Tianyu Du, Heqing Huang, Hao Peng, Zhe Liu
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.07496
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-08
+updated_at: 2026-03-21
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - computer-use
+  - multi-agent
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, computer-use, multi-agent, reasoning, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.07496

papers/items/2026-2603-07557-agentraft-automated-detection-of-data-over-exposure-in-llm-agents.md

@@ -0,0 +1,62 @@
+# Paper: AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents
+
+---
+type: paper
+title: "AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents"
+authors: Yixi Lin, Jiangrong Wu, Yuhong Nan, Xueqiang Wang, Xinyuan Zhang, Zibin Zheng
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.07557
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-08
+updated_at: 2026-03-08
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, agent-safety, rag, reasoning, tool-use
+- arXiv categories: cs.SE
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.07557

papers/items/2026-2603-07980-onemillion-bench-how-far-are-language-agents-from-human-experts.md

@@ -0,0 +1,63 @@
+# Paper: \$OneMillion-Bench: How Far are Language Agents from Human Experts?
+
+---
+type: paper
+title: "\\$OneMillion-Bench: How Far are Language Agents from Human Experts?"
+authors: Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.07980
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-09
+updated_at: 2026-03-09
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - planning
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, planning, reasoning, tool-use
+- arXiv categories: cs.LG, cs.AI, cs.CL
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.07980

papers/items/2026-2603-08721-kernelcraft-benchmarking-for-agentic-close-to-metal-kernel-generation-on-emergin.md

@@ -0,0 +1,62 @@
+# Paper: KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
+
+---
+type: paper
+title: "KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware"
+authors: Jiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao, Cheng Zhang, Binglei Lou, Erwei Wang, Jianyi Cheng, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.08721
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-10
+updated_at: 2026-05-29
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - reasoning
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AR
+  - cs.LG
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, reasoning, workflow-agent
+- arXiv categories: cs.AR, cs.LG, cs.SE
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.08721

papers/items/2026-2603-09002-security-considerations-for-multi-agent-systems.md

@@ -0,0 +1,66 @@
+# Paper: Security Considerations for Multi-agent Systems
+
+---
+type: paper
+title: Security Considerations for Multi-agent Systems
+authors: Tam Nguyen, Moses Ndebugre, Dheeraj Arremsetty
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.09002
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-09
+updated_at: 2026-04-26
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - computer-use
+  - memory
+  - multi-agent
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, computer-use, memory, multi-agent, planning, rag, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.09002

papers/items/2026-2603-10492-human-ai-co-reasoning-for-clinical-diagnosis-with-evidence-integrated-language-a.md

@@ -0,0 +1,63 @@
+# Paper: Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent
+
+---
+type: paper
+title: Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent
+authors: Zhongzhen Huang, Yan Ling, Hong Chen, Ye Feng, Li Wu, Linjie Mu, Shaoting Zhang, Xiaofan Zhang, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.10492
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-11
+updated_at: 2026-03-18
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - multi-agent
+  - rag
+  - reasoning
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, agent-safety, multi-agent, rag, reasoning, workflow-agent
+- arXiv categories: cs.CL
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.10492

papers/items/2026-2603-11088-the-attack-and-defense-landscape-of-agentic-ai-a-comprehensive-survey.md

@@ -0,0 +1,61 @@
+# Paper: The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
+
+---
+type: paper
+title: "The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey"
+authors: Juhee Kim, Xiaoyuan Liu, Zhun Wang, Shi Qiu, Bo Li, Wenbo Guo, Dawn Song
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.11088
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-11
+updated_at: 2026-03-11
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, tool-use, workflow-agent
+- arXiv categories: cs.CR, cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.11088

papers/items/2026-2603-11890-quare-quality-aware-requirements-analysis-through-multi-agent-dialectical-negoti.md

@@ -0,0 +1,61 @@
+# Paper: QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation
+
+---
+type: paper
+title: "QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation"
+authors: Haowei Cheng, Milhan Kim, Foutse Khomh, Teeradaj Racharak, Nobukazu Yoshioka, Naoyasu Ubayashi, Hironori Washizaki
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.11890
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-12
+updated_at: 2026-06-05
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - multi-agent
+  - rag
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, multi-agent, rag
+- arXiv categories: cs.SE
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.11890

papers/items/2026-2603-15309-cctu-a-benchmark-for-tool-use-under-complex-constraints.md

@@ -0,0 +1,61 @@
+# Paper: CCTU: A Benchmark for Tool Use under Complex Constraints
+
+---
+type: paper
+title: "CCTU: A Benchmark for Tool Use under Complex Constraints"
+authors: Junjie Ye, Guoqiang Zhang, Wenjie Fu, Tao Gui, Qi Zhang, Xuanjing Huang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.15309
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-16
+updated_at: 2026-03-16
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, rag, tool-use
+- arXiv categories: cs.CL, cs.AI
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.15309

papers/items/2026-2603-15666-compiled-memory-not-more-information-but-more-precise-instructions-for-language-.md

@@ -0,0 +1,59 @@
+# Paper: Compiled Memory: Not More Information, but More Precise Instructions for Language Agents
+
+---
+type: paper
+title: "Compiled Memory: Not More Information, but More Precise Instructions for Language Agents"
+authors: James Rhodes, George Kang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.15666
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-12
+updated_at: 2026-03-12
+status: queued
+relevance: high
+topics:
+  - memory
+  - rag
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: memory, rag
+- arXiv categories: cs.AI
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.15666

papers/items/2026-2603-16734-differential-harm-propensity-in-personalized-llm-agents-the-curious-case-of-ment.md

@@ -0,0 +1,62 @@
+# Paper: Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure
+
+---
+type: paper
+title: "Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure"
+authors: Caglar Yildirim
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.16734
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-17
+updated_at: 2026-03-17
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - memory
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 20
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, memory, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 20
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.16734

papers/items/2026-2603-17392-agentic-cognitive-profiling-realigning-automated-alzheimer-s-disease-detection-w.md

@@ -0,0 +1,61 @@
+# Paper: Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity
+
+---
+type: paper
+title: "Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity"
+authors: Jiawen Kang, Kun Li, Dongrui Han, Jinchao Li, Junan Li, Lingwei Meng, Xixin Wu, Helen Meng
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.17392
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-18
+updated_at: 2026-03-18
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.MA
+  - cs.IR
+  - q-bio.NC
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: agent-evaluation, tool-use
+- arXiv categories: cs.MA, cs.IR, q-bio.NC
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.17392

papers/items/2026-2603-18245-who-tests-the-testers-systematic-enumeration-and-coverage-audit-of-llm-agent-too.md

@@ -0,0 +1,63 @@
+# Paper: Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
+
+---
+type: paper
+title: Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
+authors: Xuan Chen, Lu Yan, Ruqi Zhang, Xiangyu Zhang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.18245
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-18
+updated_at: 2026-03-18
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.SE
+  - cs.CR
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 18
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, rag, tool-use, workflow-agent
+- arXiv categories: cs.SE, cs.CR
+- collection score: 18
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.18245

papers/items/2026-2603-19469-a-framework-for-formalizing-llm-agent-security.md

@@ -0,0 +1,61 @@
+# Paper: A Framework for Formalizing LLM Agent Security
+
+---
+type: paper
+title: A Framework for Formalizing LLM Agent Security
+authors: Vincent Siu, Jingxuan He, Kyle Montgomery, Zhun Wang, Neil Gong, Chenguang Wang, Dawn Song
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.19469
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-19
+updated_at: 2026-03-19
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - memory
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, memory, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.19469

papers/items/2026-2603-19684-tsegagent-zero-shot-tooth-segmentation-via-geometry-aware-vision-language-agents.md

@@ -0,0 +1,62 @@
+# Paper: TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents
+
+---
+type: paper
+title: "TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents"
+authors: Shaojie Zhuang, Lu Yin, Guangshun Wei, Yunpeng Li, Xilu Wang, Yuanfeng Zhou
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.19684
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-20
+updated_at: 2026-06-23
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - coding-agent
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CV
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, coding-agent, rag, reasoning, tool-use
+- arXiv categories: cs.CV
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.19684

papers/items/2026-2603-21357-agenther-hindsight-experience-replay-for-llm-agent-trajectory-relabeling.md

@@ -0,0 +1,62 @@
+# Paper: AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
+
+---
+type: paper
+title: "AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling"
+authors: Liang Ding
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.21357
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-22
+updated_at: 2026-05-10
+status: queued
+relevance: high
+topics:
+  - computer-use
+  - memory
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: computer-use, memory, tool-use, workflow-agent
+- arXiv categories: cs.AI, cs.CL
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.21357

papers/items/2026-2603-21564-toward-a-theory-of-hierarchical-memory-for-language-agents.md

@@ -0,0 +1,64 @@
+# Paper: Toward a Theory of Hierarchical Memory for Language Agents
+
+---
+type: paper
+title: Toward a Theory of Hierarchical Memory for Language Agents
+authors: Yashar Talebirad, Ali Parsaee, Csongor Y. Szepesvari, Amirhossein Nadiri, Osmar Zaiane
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.21564
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-23
+updated_at: 2026-03-23
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - memory
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.IR
+  - cs.AI
+  - cs.IT
+  - cs.SI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, memory, rag, tool-use
+- arXiv categories: cs.IR, cs.AI, cs.IT, cs.SI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.21564

papers/items/2026-2603-24257-memory-augmented-vision-language-agents-for-persistent-and-semantically-consiste.md

@@ -0,0 +1,60 @@
+# Paper: Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning
+
+---
+type: paper
+title: Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning
+authors: Tommaso Galliena, Stefano Rosa, Tommaso Apicella, Pietro Morerio, Alessio Del Bue, Lorenzo Natale
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.24257
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-25
+updated_at: 2026-03-30
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - embodied-agent
+  - memory
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CV
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, embodied-agent, memory
+- arXiv categories: cs.CV
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.24257

papers/items/2026-2603-25353-safeguard-asf-sr-agentic-humanoid-robot-system-for-autonomous-industrial-safety.md

@@ -0,0 +1,62 @@
+# Paper: SafeGuard ASF: SR Agentic Humanoid Robot System for Autonomous Industrial Safety
+
+---
+type: paper
+title: "SafeGuard ASF: SR Agentic Humanoid Robot System for Autonomous Industrial Safety"
+authors: Thanh Nguyen Canh, Thang Tran Viet, Thanh Tuan Tran, Ben Wei Lim
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.25353
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-26
+updated_at: 2026-03-26
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - embodied-agent
+  - reasoning
+  - tool-use
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.RO
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, embodied-agent, reasoning, tool-use, world-model
+- arXiv categories: cs.RO
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.25353

papers/items/2026-2603-27148-safetydrift-predicting-when-ai-agents-cross-the-line-before-they-actually-do.md

@@ -0,0 +1,60 @@
+# Paper: SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do
+
+---
+type: paper
+title: "SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do"
+authors: Aditya Dhodapkar, Farhaan Pishori
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.27148
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-28
+updated_at: 2026-03-28
+status: queued
+relevance: high
+topics:
+  - agent-safety
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-safety, tool-use
+- arXiv categories: cs.CR, cs.AI
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.27148

papers/items/2026-2603-28166-evaluating-privilege-usage-of-agents-with-real-world-tools.md

@@ -0,0 +1,63 @@
+# Paper: Evaluating Privilege Usage of Agents with Real-World Tools
+
+---
+type: paper
+title: Evaluating Privilege Usage of Agents with Real-World Tools
+authors: Quan Zhang, Lianhang Fu, Lvsi Lian, Gwihwan Go, Yujue Wang, Chijin Zhou, Yu Jiang, Geguang Pu
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.28166
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-30
+updated_at: 2026-04-20
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, rag, tool-use, workflow-agent
+- arXiv categories: cs.CR, cs.AI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.28166

papers/items/2026-2603-28428-synergy-a-next-generation-general-purpose-agent-for-open-agentic-web.md

@@ -0,0 +1,64 @@
+# Paper: Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web
+
+---
+type: paper
+title: "Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web"
+authors: Xiaohang Nie, Zihan Guo, Kezhuo Yang, Zhichong Zheng, Bochen Ge, Shuai Pan, Zeyi Chen, Youling Xiang, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.28428
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-30
+updated_at: 2026-03-30
+status: queued
+relevance: high
+topics:
+  - coding-agent
+  - embodied-agent
+  - memory
+  - multi-agent
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CY
+  - cs.MA
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: function-calling
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling
+- inferred topics: coding-agent, embodied-agent, memory, multi-agent, rag, tool-use
+- arXiv categories: cs.CY, cs.MA
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.28428

papers/items/2026-2603-28900-robust-multi-agent-reinforcement-learning-for-small-uas-separation-assurance-und.md

@@ -0,0 +1,64 @@
+# Paper: Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing
+
+---
+type: paper
+title: Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing
+authors: Alex Zongo, Filippos Fotiadis, Ufuk Topcu, Peng Wei
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2603.28900
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-03-30
+updated_at: 2026-03-30
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - multi-agent
+  - world-model
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.RO
+  - cs.AI
+  - cs.LG
+  - eess.SY
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 13
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, multi-agent, world-model
+- arXiv categories: cs.RO, cs.AI, cs.LG, eess.SY
+- collection score: 13
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2603.28900

papers/items/2026-2604-02022-atbench-a-diverse-and-realistic-agent-trajectory-benchmark-for-safety-evaluation.md

@@ -0,0 +1,62 @@
+# Paper: ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
+
+---
+type: paper
+title: "ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis"
+authors: Yu Li, Haoyu Luo, Yuejin Xie, Yuqian Fu, Zhonghao Yang, Shuai Shao, Qihan Ren, Wanying Qu, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.02022
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-02
+updated_at: 2026-05-13
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - planning
+  - rag
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 20
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, planning, rag, tool-use
+- arXiv categories: cs.AI
+- collection score: 20
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.02022

papers/items/2026-2604-02155-brief-is-better-non-monotonic-chain-of-thought-budget-effects-in-function-callin.md

@@ -0,0 +1,61 @@
+# Paper: Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents
+
+---
+type: paper
+title: "Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents"
+authors: Xuan Qi
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.02155
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-02
+updated_at: 2026-04-02
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: function-calling, language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: function-calling, language-agent
+- inferred topics: agent-evaluation, rag, reasoning, tool-use
+- arXiv categories: cs.CL
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.02155

papers/items/2026-2604-03098-co-evolution-of-policy-and-internal-reward-for-language-agents.md

@@ -0,0 +1,63 @@
+# Paper: Co-Evolution of Policy and Internal Reward for Language Agents
+
+---
+type: paper
+title: Co-Evolution of Policy and Internal Reward for Language Agents
+authors: Xinyu Wang, Hanwei Wu, Jingwei Song, Shuyuan Zhang, Jiayi Zhang, Fanqi Kong, Tung Sum Thomas Kwok, Xiao-Wen Chang, et al.
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.03098
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-03
+updated_at: 2026-04-03
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - computer-use
+  - planning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+  - cs.AI
+  - cs.CL
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, computer-use, planning, tool-use
+- arXiv categories: cs.LG, cs.AI, cs.CL
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.03098

papers/items/2026-2604-03242-draft-task-decoupled-latent-reasoning-for-agent-safety.md

@@ -0,0 +1,62 @@
+# Paper: DRAFT: Task Decoupled Latent Reasoning for Agent Safety
+
+---
+type: paper
+title: "DRAFT: Task Decoupled Latent Reasoning for Agent Safety"
+authors: Lin Wang, Junfeng Fang, Dan Zhang, Fei Shen, Xiang Wang, Tat-Seng Chua
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.03242
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-02-11
+updated_at: 2026-02-11
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+  - reasoning
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.LG
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 17
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, rag, reasoning, tool-use
+- arXiv categories: cs.LG
+- collection score: 17
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.03242

papers/items/2026-2604-04131-profile-then-reason-bounded-semantic-complexity-for-tool-augmented-language-agen.md

@@ -0,0 +1,62 @@
+# Paper: Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
+
+---
+type: paper
+title: "Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents"
+authors: Paulo Akira F. Enabe
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.04131
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-05
+updated_at: 2026-04-05
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - rag
+  - reasoning
+  - tool-use
+  - workflow-agent
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 16
+collection_queries: language-agent
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: language-agent
+- inferred topics: agent-evaluation, rag, reasoning, tool-use, workflow-agent
+- arXiv categories: cs.AI
+- collection score: 16
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.04131

papers/items/2026-2604-04426-shieldnet-network-level-guardrails-against-emerging-supply-chain-injections-in-a.md

@@ -0,0 +1,60 @@
+# Paper: ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems
+
+---
+type: paper
+title: "ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems"
+authors: Zhuowen Yuan, Zhaorun Chen, Zhen Xiang, Nathaniel D. Bastian, Seyyed Hadi Hashemi, Chaowei Xiao, Wenbo Guo, Bo Li
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.04426
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-06
+updated_at: 2026-04-06
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - tool-use
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.AI
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 15
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, tool-use
+- arXiv categories: cs.AI
+- collection score: 15
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.04426

papers/items/2026-2604-06762-arulecon-agentic-security-rule-conversion.md

@@ -0,0 +1,60 @@
+# Paper: ARuleCon: Agentic Security Rule Conversion
+
+---
+type: paper
+title: "ARuleCon: Agentic Security Rule Conversion"
+authors: Ming Xu, Hongtai Wang, Yanpei Guo, Zhengmin Yu, Weili Han, Hoon Wei Lim, Jin Song Dong, Jiaheng Zhang
+year: 2026
+venue: arXiv
+url: https://arxiv.org/abs/2604.06762
+code_url:
+source: arxiv
+collected_at: 2026-07-08
+published_at: 2026-04-08
+updated_at: 2026-04-08
+status: queued
+relevance: high
+topics:
+  - agent-evaluation
+  - agent-safety
+  - rag
+methods:
+  -
+benchmarks:
+  -
+models:
+  -
+datasets:
+  - cs.CR
+related_concepts:
+  -
+related_jobs:
+  -
+related_experiments:
+  -
+related_projects:
+  -
+collection_score: 14
+collection_queries: agent-safety
+---
+
+## One-line Takeaway
+
+Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.
+
+## Why Collected
+
+- matched queries: agent-safety
+- inferred topics: agent-evaluation, agent-safety, rag
+- arXiv categories: cs.CR
+- collection score: 14
+
+## Review Checklist
+
+- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
+- Does it include a benchmark, dataset, code, or reproducible experimental setup?
+- Should it be promoted from `queued` to `skimmed` or `summarized`?
+
+## Links
+
+- arXiv: https://arxiv.org/abs/2604.06762