LongRCA Bench
Explore score history ↗LongRCA Bench is a benchmark for diagnosing responsible roles and root causes in long-horizon agent failures. It comprises 1,140 failed trajectories across five domains, with human labels for the responsible role and the earliest decisive root-cause step. Evaluation focuses on responsible-role accuracy and exact root-step accuracy.
- Released
- 2026-08-15
- Institutions
- Chinese Academy of Sciences · Computer Network Information Center · Chongqing University
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
LongRCA Bench paper
No reported scores are on record for this benchmark yet.