agent/papers/items/2026-2606-26806-memory-depth-not-memory-access-selective-parametric-consolidation-for-long-runni.md

Paper: Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents

---

type: paper title: "Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents" authors: Haoliang Han year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.26806 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-25 updated_at: 2026-06-25 status: queued relevance: high topics:

• agent-evaluation
• memory
• rag methods:

benchmarks:

models:

datasets:

• cs.AI
• cs.LG 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, rag
• arXiv categories: cs.AI, cs.LG
• 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/2606.26806