{
  "id": 3938,
  "url": "https://arxiv.org/abs/2605.21984v1",
  "title": "Echo: Learning from Experience Data via User-Driven Refinement",
  "summary": "Static \"human data\" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from \"experience data\" - interactions between agents and their environments - promises to transcend these barriers. Today, the widespread deployment of AI agents grants us low-cost access to massive streams of such real-world experience. However, raw interaction logs are inherently noisy, filled with trial-and-error and low information density, rendering them",
  "authors": "Hande Dong, Xiaoyun Liang, Jiarui Yu, Jiayi Lin, Changqing Ai, Feng Liu et al.",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-21T04:34:00.000Z",
  "fetched_at": "2026-07-14T16:30:36.743Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3938",
  "original_url": "https://arxiv.org/abs/2605.21984v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}