Hugging Face's logo
Activity Feed

AI & ML interests

Harness evaluation

Recent Activity
HengjieZhu  submitted a paper about 24 hours ago
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
HengjieZhu  updated a dataset 1 day ago
TraceLite-AI/TraceTrial-Bench
HengjieZhu  published a dataset 1 day ago
TraceLite-AI/TraceTrial-Bench
View all activity

Papers

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

View all Papers

TraceLite-AI 's datasets 2