arxiv:2602.06527
Shengxuan Qiu
SXQiu
AI & ML interests
Efficient AI, LLM Reasoning
Recent Activity
upvoted a paper 14 days ago
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents authored a paper 16 days ago
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction liked a dataset 16 days ago
LulaCola/AgentProcessBenchOrganizations
None yet