{
  "id": 909,
  "url": "https://arxiv.org/abs/2606.17591v1",
  "title": "Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning",
  "summary": "Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes. However, in non-stationary environments these agents face a retention-forgetting dilemma: retaining stale insights causes negative transfer, while discarding them causes catastrophic for",
  "authors": "Yanwei Cui, Xing Zhang, Yulong Zhang, Li Shao, Xiaofeng Shi, Guanghui Wang et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-16T06:55:55.000Z",
  "fetched_at": "2026-07-14T14:14:54.531Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/909",
  "original_url": "https://arxiv.org/abs/2606.17591v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}