Google发布CI流程中的程序修复代理FlowAgent
Google的FlowAgent能自动修复CI测试失败,开发者接受率近半,实际提升开发效率。
Google研究人员提出FlowAgent,在预提交测试失败上运行ReAct样式的生成-验证循环。该系统通过两个弃权过滤器决定是否展示修复方案,一个在执行前运行,一个在执行后运行。在195个真实失败的手动审查中,67.18%的修复是正确的。Google全面部署后,该系统在295,508次代码变更中建议了修复方案。
Great paper from Google on program repair agents inside CI. (bookmark it) They propose FlowAgent, which runs a ReAct-style generate-and-validate loop on pre-submit test failures and shows the fix inside Google's code review tools. Two abstention filters decide whether a fix is worth showing. One runs before execution and one after, so weak suggestions never reach the developer. In a manual review of 195 real failures, 67.18% of its fixes were correct. After the Google-wide launch, it suggested fixes on 295,508 changes. Developers previewed 65,069 and applied 28,554. Paper: arxiv.org/abs/2610.07289 Chat with Paper: academy.dair.ai/papers/catchin… 💬 9 🔄 4 ❤️ 14 👀 1482 📊 11 ⚡