Chenxi Huang, Haonan Wang, Jinghe Zhang, Aleksandr Nogikh, Franjo Ivančić, Petros Maniatis, Eugene Wu, Kostis Kaffes · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29332 · open-access PDF
Agen pengkodean semakin mampu memperbaiki bug dunia nyata, namun mereka masih berjuang dengan basis kode sistem besar seperti kernel Linux. Untuk memahami mengapa, kami menguji bagaimana agen berpendapat tentang eksekusi dalam basis kode ini melalui alasan crash: memprediksi dari kode sumber apakah input yang diberikan akan crash sistem. prediksi yang benar saja, bagaimanapun, tidak menetapkan kemampuan ini, karena itu mungkin berasal dari hanya menemukan kode mencurigakan. Dalam makalah ini, kami mengusulkan intervensi sumber: kami menggabungkan pohon sumber yang berbeda dengan komisi tunggal, sehingga input yang sama hanya crash satu dari mereka, dan
Machine translation (Meta M2M100); the English original follows.
Coding agents are increasingly capable of fixing real-world bugs, yet they still struggle with large systems codebases such as the Linux kernel. To understand why, we test how agents reason about execution in these codebases through crash reasoning: predicting from source code whether a given input crashes the system. A correct prediction alone, however, does not establish this ability, since it may come from merely spotting suspicious code. In this paper, we propose source interventions: we pair source trees that differ by a single commit, so that the same input crashes only one of them, and
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=2610.29332, 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