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

Spanish

Los índices de vulnerabilidad y la investigación de ingeniería de software dependen de la reconstrucción del software histórico. Sin embargo, las construcciones dependen de recursos externos, como imágenes de base y paquetes, que cambian independientemente del código fuente. En este estudio, examinamos esta degradación ambiental en 14.159 casos de OSS-Fuzz. Descubrimos que el 69.7% ya no completa la reconstrucción y la verificación, y que la mayoría de los fallos comparten un pequeño número de síntomas de fallos recurrentes a un agente por caso. Por lo tanto, un fallo recurrente puede ser diagnosticado una vez y su reparación reutilizada. Presentamos Relay, un marco híbrido que utiliza un LLM para derivar y validar las reglas de reparación deterministas de fallos representativos, las reutiliza sin llamadas de

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