Haoze Wu

WaitHZ

·

https://waithz.github.io/

AI & ML interests

RL, LLM, Agent

Recent Activity

updated a dataset about 23 hours ago

WaitHZ/SSPO-data

authored a paper 27 days ago

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

upvoted a paper 27 days ago

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

View all activity

Organizations

WaitHZ 's papers 5

arxiv:2608.12764

arxiv:2510.25726

arxiv:2508.21188

arxiv:2506.20495

arxiv:2406.12375