{
  "id": 14961,
  "url": "https://arxiv.org/abs/2607.27834v1",
  "title": "MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory",
  "summary": "Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior. Existing systems improve storage and retrieval, but they do not provide a transaction boundary for reliable updates and recovery. We therefore propose MemTxn, a governance layer outside the answer model. MemTxn verifies whether an update is supported by its source. It also selects the visible version when facts conflic",
  "authors": "Hanshuai Cui, Zhiqing Tang, Zhi Yao, Fanshuai Meng, Qianli Ma, Weijia Jia",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-30T08:15:02.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/14961",
  "original_url": "https://arxiv.org/abs/2607.27834v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}