{
  "id": 6248,
  "url": "https://arxiv.org/abs/2604.05955v1",
  "title": "Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution",
  "summary": "Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with project-specific design constraints, such as architectural conventions, error-handling policies, and maintainability requirements, which are rarely encoded in tests and are often documented only implicitly in code review discussions. This paper introduces \\textit{",
  "authors": "Kai Yu, Zhenhao Zhou, Junhao Zeng, Ying Wang, Xueying Du, Zhiqiang Yuan et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-07T14:47:27.000Z",
  "fetched_at": "2026-07-14T16:32:20.057Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6248",
  "original_url": "https://arxiv.org/abs/2604.05955v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}