{
  "id": 19433,
  "url": "https://arxiv.org/abs/2608.13547v1",
  "title": "QuoteBench: How Matched Scores Can Hide Command-Path Failures",
  "summary": "LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14 incident-derived families, crossing the generation contract with the execution transport around one deliberately unescaped added parser. Escaping at the interpolation point re",
  "authors": "Shangao Li, Yao Zhang, Volker Tresp, Yuanyuan Yang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T17:57:20.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/19433",
  "original_url": "https://arxiv.org/abs/2608.13547v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}