跳到正文
原文
omarsar0· @omarsar0 · X·· 2 天前AI 评分56

Google 论文提出 CI 内程序修复智能体 FlowAgent

AI 导读

Google 的一篇论文提出 FlowAgent,它在预提交测试失败上运行 ReAct 式生成-验证循环,并在 Google 代码审查工具中展示修复建议;两道弃权过滤器分别在执行前后判断修复是否值得展示,避免弱建议触达开发者。

正文 · 原文

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/catch…

来源:omarsar0 · x.com