{
  "id": 5918,
  "url": "https://arxiv.org/abs/2604.12007v1",
  "title": "When to Forget: A Memory Governance Primitive",
  "summary": "Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories to trust, suppress, or deprecate as the agent's task distribution shifts. Write-time importance scores are static; dynamic management systems use LLM judgment or structural heuristics rather than outcome feedback. This paper proposes Memory Worth (MW): a two-counter per-memory signal that tracks how often a memory co-occurs with successful versus ",
  "authors": "Baris Simsek",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T19:54:14.000Z",
  "fetched_at": "2026-07-14T16:32:06.468Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5918",
  "original_url": "https://arxiv.org/abs/2604.12007v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}