Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Zhaorun Chen, Bo Li, Weiyan Shi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28934 · open-access PDF
코딩 에이전트는 이제 자율적으로 작업을 완료하고, 예제, 소프트웨어 환경 및 구성과 같은 실제 상태를 수정합니다.그러나 그들은 제한된 백업 인식을 보여줍니다 : 작업이 나중에 필요할 수있는 상태를 수정하고 사전에 보존한다는 것을 인식합니다. 백업 인식을 평가하기 위해 우리는 RegretBench를 소개합니다.RegretBench는 X.com, GitHub 및 Stack Overflow와 같은 플랫폼에서 보고 된 후회 순간에 기초한 205 개의 실행 가능한 작업의 기준입니다.
Machine translation (Meta M2M100); the English original follows.
Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness: recognizing that an action will modify state that may later be needed, and preserving it beforehand. To evaluate backup awareness, we introduce RegretBench, a benchmark of 205 executable tasks grounded in regret moments reported on platforms such as X.com, GitHub, and Stack Overflow, where users explicitly regretted not preserving state they later needed. Across six frontier models, agents complete 86.1% of
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28934, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange