Newest papers

Do Coding Agents Understand Why Systems Crash---and Why They Don't?

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

Portuguese

Os agentes de codificação são cada vez mais capazes de corrigir bugs do mundo real, mas eles ainda lutam com grandes bases de código de sistemas, como o kernel do Linux. Para entender por que, testamos como os agentes raciocinam sobre a execução nessas bases de código através de raciocínio de colisão: prever a partir do código-fonte se uma entrada dada colisiona com o sistema. Uma previsão correta sozinha, no entanto, não estabelece essa capacidade, já que pode vir de simplesmente detectar código suspeito. Neste artigo, propomos intervenções de fonte: emparelhamos árvores-fonte que diferem por um único comitê, de modo que a mesma entrada colisione apenas um deles, e

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange