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
Los agentes de codificación son cada vez más capaces de corregir los errores del mundo real, pero todavía luchan con grandes bases de código de sistemas como el núcleo de Linux. Para entender por qué, probamos cómo los agentes razonan sobre la ejecución en estas bases de código a través del razonamiento de colapso: prediciendo desde el código fuente si una entrada dada colapsa el sistema. Una predicción correcta por sí sola, sin embargo, no establece esta capacidad, ya que puede provenir simplemente de detectar código sospechoso.
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