Preprint
Aug 2026
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
This work introduces LongRCA Bench, comprising 1,140 failed trajectories across five domains without injected errors, and presents Root-Cause Trajectory Attribution (RCTA), a training-free method that retrieves candidate error steps from segment summaries and traces them to available earlier handoff instructions.
Yunfei Zhang, Boyu Feng, Changhua Pei et al.
· 1 citation