{
  "id": 6440,
  "url": "https://arxiv.org/abs/2604.02280v1",
  "title": "Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency",
  "summary": "Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention. This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimizatio",
  "authors": "Payal Fofadiya, Sunil Tiwari",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-02T17:14:53.000Z",
  "fetched_at": "2026-07-14T16:32:28.612Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6440",
  "original_url": "https://arxiv.org/abs/2604.02280v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}