#artificial intelligence
Feb 2026
AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
To mitigate the human cost of failure attribution, AgentRx is presented, an automated diagnostic framework that pinpoints the critical failure step in a failed agent trajectory and improves step localization by 75% on average over prior work, while providing failure category attribution.
Shraddha Barke, Arnav Goyal, Alind Khare et al.
· arXiv.org · 42 citations
· ⚡5