{
  "id": 3414221,
  "title": "CAFE: Self-Improving Search Agents Need Co-Evolving Feedback",
  "url": "https://urgent.news/2026/08/25/cafe-self-improving-search-agents-need-co-evolving-feedback",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-25T16:39:00.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.24794v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound. Treating corrective feedback as a learned in-trajectory intervention couples the two roles: the agent must decide when to request and use feedback, while the critic must infer useful corrections from…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}