{
  "id": 14857878,
  "title": "KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents",
  "url": "https://urgent.news/2026/10/15/knowgpo-knowledge-grouped-policy-optimization-for-search-agents",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-15T17:52:33.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.22331v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision methods aim to assign credit at finer granularity, but they typically anchor…",
  "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."
}