Olivier Nourry, Yoshiki Higo · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27784 · cited by 0 works (OpenAlex) · open-access PDF
No entanto, as construções dependem de recursos externos, como imagens de base e pacotes, que mudam independentemente do código-fonte. Neste estudo, examinamos esta degradação ambiental em 14.159 casos de OSS-Fuzz. Descobrimos que 69.7% já não têm reconstrução e verificação completas, e que a maioria das falhas compartilham um pequeno número de sintomas de falha recorrentes. Uma falha recorrente pode, portanto, ser diagnosticada uma vez e sua reparação reutilizada. Nós apresentamos o Relay, uma estrutura híbrida que usa um LLM para derivar e validar regras de reparação deterministas de falhas representativas, reúne-as sem chamadas de modelo, e escala os casos não resolvidos por regras para um agente por caso. Nós avaliamos o Relay em campanhas de
Machine translation (Meta M2M100); the English original follows.
Vulnerability benchmarks and software engineering research depend on rebuilding historical software. Yet builds rely on external resources, such as base images and packages, that change independently of the source code. In this study, we examine this environment decay on 14,159 OSS-Fuzz cases. We find that 69.7% no longer complete reconstruction and verification, and that most failures share a small number of recurring failure symptoms. A recurring failure can therefore be diagnosed once and its repair reused. We present Relay, a hybrid framework that uses an LLM to derive and validate deterministic repair rules from representative failures, reuses them without model calls, and escalates cases unresolved by rules to a per-case agent. We evaluate Relay in human-guided and fully automated rule-derivation campaigns and compare it with a per-case agent approach. We find that rule derivation can be fully automated, and that reusable rules restore as many builds as per-case agents with fewer build executions. However, agents restore cases that the rules cannot. Our results show that a hybrid approach that applies rules first and escalates the remaining cases to an agent restores more builds than either approach alone and at a lower cost than using agents alone.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Reuse, Computer science, Knowledge base, Risk analysis (engineering), Software engineering, Software
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27784, 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