{
  "id": 17915,
  "url": "https://arxiv.org/abs/2608.07429v1",
  "title": "TEPA: Revoking Stale Memories for Conflict-Robust Language Agents",
  "summary": "Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represe",
  "authors": "Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-07T17:16:33.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/17915",
  "original_url": "https://arxiv.org/abs/2608.07429v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}