Google's FlowAgent fixes CI test failures: 67% correct on 195 cases, 28,554 fixes applied after launch
omarsar0 · x · 2026-10-09
A notable Google paper on program repair agents inside CI, as highlighted by Sewon Min:
- How it works: FlowAgent runs a ReAct-style generate-and-validate loop on pre-submit test failures and surfaces the fix inside Google's code review tools.
- Two abstention filters: one before execution and one after, so weak suggestions never reach developers.
- Results: in a manual review of 195 real failures, 67.18% of fixes were correct. After a Google-wide launch, it suggested fixes on 295,508 changes; developers previewed 65,069 and applied 28,554.
More from coding & agent
- Taming Codex's nagging auto-review with custom policies and agents.md guidance — pvncher · 2026-10-09
- LukeW: designers, we need a gorgeous mobile app for managing agents across devices — LukeW · 2026-10-09
- A Playable 3D Boat Game Embedded in an X Post, Built by Claude Opus — prasenx · 2026-10-09
- ProximalHQ's training setup lifts Qwen3.8-27B to 37.2% Pass@1 on DeepSWE, up 8.4 points — aryaman2020 · 2026-10-09
- edith-1 monitors agent traces, beats Sonnet-5.5 on balanced accuracy at 1/274 the cost — xennygrimmato_ · 2026-10-09
- How edith-1 works: probabilistic filter plus expensive agent judge for flagged runs — xennygrimmato_ · 2026-10-09