Caijun Xu
SII-Molu
AI & ML interests
None yet
Recent Activity
authored a paper about 13 hours ago
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders upvoted a paper about 19 hours ago
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders upvoted a paper about 1 month ago
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning