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

Korean

그럼에도 불구하고, 건축은 원본 코드와 독립적으로 변경되는 기본 이미지 및 패키지와 같은 외부 자원에 의존합니다. 이 연구에서 우리는 14.159 OSS-Fuzz 사례에서이 환경 붕괴를 검사합니다. 우리는 69.7%가 더 이상 완전한 재건 및 검증을하지 않으며 대부분의 실패는 규칙에 의해 해결되지 않은 몇 가지 실패 증상을 공유한다는 것을 발견합니다. 따라서 반복 실패는 한 번 진단되고 복구가 재사용 될 수 있습니다. 우리는 Relay를 소개하고 LLM을 사용하여 대표적인 실패에서 결정적인 복구 규칙을 추출하고 검증하는 하이브리드 프레임 워크를 소개합니다. 우리는 규칙이 자동화 된 사례를 사용하여 완전히 자동화되고 많은 사례를 사용하여 복구 할 수있는

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