Google 论文提出 FlowAgent，在代码合并前自动修复失败测试

AI 导读

Google 论文介绍 FlowAgent，可在代码合并前捕获 CI 测试失败，并让 AI 智能体持续编辑、构建和重跑测试直至通过，修复结果会附根因说明进入代码评审。专家评估其对 195 个真实失败案例的修复正确率为 67.18%，开发者已在生产环境应用 28,554 个修复。其运行时间中位数为 9.85 分钟，而开发者开始编辑前的中位数为 27.48 分钟，但部分修复到达时已错过合并时机。

正文 · 原文

Google paper shows that an AI agent can fix failing tests across Google, and speed decides whether developers use the fix.

Tests that fail in CI ( continuous integration) before merge pull developers out of their flow, and existing repair agents mostly work offline after merge.

They built FlowAgent, which catches each test failure and runs an agent that edits, builds, and reruns tests until they pass. Verified fixes appear in code review with a short note on the root cause.

Experts judged 67.18% of its fixes correct on 195 real failures, and developers applied 28,554 fixes in production. Its median run took 9.85 minutes, versus a 27.48-minute median before developers start editing, yet many fixes still arrived too late.