arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.27784cs.SEcs.AI
收藏

RELAY:通过规则复用与智能体修复扩展历史构建恢复能力

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

The University of Osaka(大阪大学)

Olivier Nourry, Yoshiki Higo

AI总结:

本研究针对历史软件构建因外部资源变化导致的衰减问题,提出RELAY混合框架,结合规则复用与智能体修复,可恢复更多构建且成本更低。

摘要:

漏洞基准测试与软件工程研究依赖于重建历史软件,但构建过程依赖于基础镜像、软件包等外部资源,这些资源会独立于源代码发生变化。本研究针对14159个OSS-Fuzz案例,考察这种环境衰减现象,发现69.7%的案例无法完成重建与验证,且多数失败具有少量重复出现的故障症状,因此重复故障可经一次诊断后复用其修复方案。我们提出RELAY,这是一种混合框架,它利用大语言模型(LLM)从代表性故障中推导并验证确定性修复规则,无需调用模型即可复用这些规则,并将规则无法解决的案例升级至专属案例智能体。我们在人工引导与完全自动化的规则推导场景中评估RELAY,并将其与专属案例智能体方法对比,发现规则推导可完全自动化,且可复用规则能恢复与专属案例智能体数量相当的构建,同时所需构建执行次数更少;不过智能体可恢复规则无法处理的案例。我们的结果表明,先应用规则再将剩余案例升级至智能体的混合方法,比单独使用任一方法能恢复更多构建,且成本低于单独使用智能体。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑