Newest papers

RELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic Repair

Olivier Nourry, Yoshiki Higo · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27784 · cited by 0 works (OpenAlex) · open-access PDF

French

Les critères de vulnérabilité et la recherche en génie logiciel dépendent de la reconstruction du logiciel historique. Néanmoins, les bâtiments reposent sur des ressources externes, telles que les images de base et les paquets, qui changent indépendamment du code source. Dans cette étude, nous examinons cette dégradation de l'environnement sur 14 159 cas OSS-Fuzz. Nous constatons que 69.7% n'ont plus de reconstruction et de vérification complètes, et que la plupart des échecs partagent un petit nombre de symptômes de défaillance récurrents. Une défaillance récurrente peut donc être diagnostiquée une fois et sa réparation réutilisée. Nous présentons Relay, un cadre hybride qui utilise un LLM

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

Abstract

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

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