{
  "id": 18031,
  "url": "https://arxiv.org/abs/2608.09072v1",
  "title": "A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents",
  "summary": "Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs. Yet existing repository-level benchmarks typically evaluate only whether the final patch passes tests. Satisfying a user request requires a long chain of interdependent reasoning and decisions: an agent must recover explicit and implicit requirements, formulate a repository-grounded implementation plan, and translate it into correct code. A pass/f",
  "authors": "Xin Zhou, Chun Yong Chong, Kisub Kim, Yun Peng, Rui Shu, Zihan Wu et al.",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T03:22:04.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18031",
  "original_url": "https://arxiv.org/abs/2608.09072v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}