Tutorials
NEW Research from Google. Integration test failures are painful because the signal is buried in messy logs. Massive output, heterogeneous sy…
NEW Research from Google. Integration test failures are painful because the signal is buried in messy logs. Massive output, heterogeneous systems, low signal-to-noise ratio, and unclear root causes. T
NEW Research from Google. Integration test failures are painful because the signal is buried in messy logs. Massive output, heterogeneous systems, low signal-to-noise ratio, and unclear root causes. This paper introduces Auto-Diagnose, an LLM-based tool deployed inside Google's Critique code review system. Auto-Diagnose analyzes failure logs, summarizes the most relevant lines, and suggests the root cause in the developer workflow where the failure is already being reviewed. The deployment numbers are notable. In a manual evaluation of 71 real-world failures, Auto-Diagnose reached 90.14% root-cause diagnosis accuracy. After Google-wide deployment, it was used across 52,635 distinct failing tests. User feedback marked it "Not helpful" in only 5.8% of cases, and it ranked #14 in helpfulness among 370 Critique tools. Paper: https://arxiv.org/abs/2604.12108 Learn to build effective AI agents in our academy: https://academy.dair.ai/
Related
- Coding agents learn from experience, but that knowledge stays locked in silos. Solve a thousand SWE tasks, and none of that wisdom helps wit…
- TEC: A Collection of Human Trial-and-error Trajectories for Problem Solving
- Smart Paste: Automatically Fixing Copy/Paste for Google Developers
Source: DAIR.AI (X) | 2026-04-16