{
  "id": 15891,
  "url": "https://arxiv.org/abs/2608.01913v1",
  "title": "Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents",
  "summary": "Deep search agents answer difficult information-seeking questions by iteratively issuing search queries to gather supporting evidence, but it remains unclear whether and how greater search effort leads to better answers. We study these questions through a trajectory-level diagnosis of long-horizon search agents. Using human-annotated document-level relevance judgments, we evaluate the evidence retrieved at each search step and separate two stages of agent behavior: what evidence an agent retriev",
  "authors": "Qi Liu, Jiaxin Mao, Fengbin Zhu, Tat-Seng Chua",
  "category": "research",
  "topics": "healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T08:46:48.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/15891",
  "original_url": "https://arxiv.org/abs/2608.01913v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}