{
  "id": 15887,
  "url": "https://arxiv.org/abs/2608.02009v1",
  "title": "HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents",
  "summary": "Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence. This creates a stopping problem: after the necessary evidence has appeared, further retrieval often adds cost, latency, and distracting context rather than useful information. We frame stopping as evidence coverage rather than generator confidence, and introduce HALT, a lightweight verification-aware policy that leaves the search agent unchanged. Given expected hop claims,",
  "authors": "Daeyoung Roh, Donghee Han",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T10:09:06.000Z",
  "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/15887",
  "original_url": "https://arxiv.org/abs/2608.02009v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}