Google 部署 AutoRepair：低延迟智能体自动修复测试失败
原标题：Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale
AI 摘要
Google 在 arXiv 发布论文，介绍其部署于内部开发工具 Critique 和 Cider 的 AI 智能体 AutoRepair，用于在持续集成系统的 pre-submit 阶段自动修复测试失败。AutoRepair 采用 ReAct 风格的生成-验证循环，并加入执行前后弃权过滤器，以满足严格的低延迟要求。论文称这是首个面向 pre-submit 外循环工作流、在关键延迟约束下运行的自动程序修复系统，并基于大规模工业数据进行了人工评估与多月生产环境部署验证。
正文节选
Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale Abstract. Manual repair of program failures is time-consuming and disruptive for software developers, particularly during the pre-submit phase where test failures occur within continuous integration systems. While Automated Program Repair has seen significant advancement through Large Language Models, existing state-of-the-art techniques primarily focus on post-submit workflows, operating offline without the low-