Yang Wan

万扬
Ph.D. Student
College of Computer Science and Technology, Zhejiang University

About

I am a Ph.D. candidate in the College of Computer Science and Technology at Zhejiang University. I received my B.Eng. (Honors) in Computer Science and Technology from Hangzhou Dianzi University.

My research aims to make reinforcement learning more efficient by extracting more learning from the experience it collects, and to make interaction with environments cheap and controllable, so that RL can scale to settings where exploration is expensive, including reinforcement learning in the real world. I am currently focusing on computer-use agents and multi-turn reinforcement learning.

Selected Papers

Mitigating Conversational Inertia in Multi-Turn Agents
Yang Wan, Zheng Cao, Zhenhao Zhang, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Linchao Zhu
ICML 2026 (Accepted)

Competitive Programming

I have been involved in competitive programming (ICPC and CCPC) for several years, earning a regional gold medal and several silver medals as a contestant, and I serve as a judge for CCPC regional contests.