Google 论文：FlowAgent 修复失败 CI 测试，正确率 67.18%
Google 造了个智能体，专修合并前挂掉的测试，专家判定近七成修复靠谱，已在生产里落地两万八千多次。
Google 发表论文介绍 FlowAgent，一个在代码合并前修复 CI 失败测试的智能体。它捕获每次测试失败后自动编辑代码、构建并重跑测试，直到通过，再把验证过的修复送入代码审查并附上根因说明。在 195 个真实失败案例上，专家判定 67.18% 的修复正确，开发者已在生产中应用 28,554 个修复。速度是采用关键：其中位运行时间 9.85 分钟，而开发者开始手动修改前的中位等待时间为 27.48 分钟，但许多修复仍来得太晚。
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.
