{
  "url": "https://appliedfrontier.nl/en/research/signal-94fdbb5e499af129/",
  "title": "Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success",
  "published": "2026-10-29",
  "excerpt": "Tool-use benchmarks often score agents by final task success, but terminal outcomes can obscure whether the intermediate tool-call trajectory was executable. We propose prefix executability",
  "content_sha256": "b8b322b21e7e6c6b535f84af3975886e875ccd728ead3e8362e2db5408629b63",
  "extracted_chars": 1673,
  "artifact_links": [
    "https://arxiv.org/abs/2610.40444"
  ],
  "arxiv_id": "2610.40444",
  "extraction_scope": "preprint_abstract_metadata",
  "full_text_available": false,
  "id": "signal-94fdbb5e499af129",
  "org": "Research community",
  "topic": "Agent systems",
  "source_kind": "preprint",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Agent systems"
  ],
  "checked_at": "2026-11-02T01:17:04+00:00",
  "first_seen": "2026-10-31T19:32:55+00:00",
  "source_hash": "d0c721373642bdcb5a31fad01ed7374b4e0027d9dbd543ef41c4a1ecb9c19d19",
  "source_url": "https://arxiv.org/abs/2610.40444",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}