{
  "id": 204405,
  "title": "ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment",
  "url": "https://urgent.news/2026/08/05/abseeker-training-long-horizon-search-agents-via-answer-backtracked",
  "topic": "finance",
  "section": "Finance & Markets",
  "published": "2026-08-05T17:41:31.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.05102v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant…",
  "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."
}