Xiao Yu

I am a third year Ph.D. student in Computer Science at Columbia University advised by Zhou Yu. Before joining the Ph.D. program, I was an undergrad also at Columbia University, majoring in Computer Science and minoring in Applied Physics.

🌟 Currently I am interested in improving the environment understanding and planning capabilities of AI agents, especially for browser/computer/phone-use.

Scalable Reinforcement Learning algorithms

World Model training methods such as Dyna

Planning Algorithms such as MCTS

🚀 My most recent work include (in chronological order):

arXiv

Reinforcement World Model Learning for LLM-based Agents

Xiao Yu, Baolin Peng, Ruize Xu, Yelong Shen, Pengcheng He, Suman Nath, Nikhil Singh, Jiangfeng Gao, Zhou Yu

Paper

ICLR 2026

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

Xiao Yu, Baolin Peng, Michel Galley, Hao Cheng, Qianhui Wu, Janardhan Kulkarni, Suman Nath, Zhou Yu, Jianfeng Gao

Paper

GitHub

ICLR 2026
(Workshop)

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents

Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu

Paper

NeurIPS 2025
(Workshop)

AI Agents for Web Testing: A Case Study in the Wild

Naimeng Ye, Xiao Yu, Ruize Xu, Tianyi Peng, Zhou Yu

Paper

GitHub

ICLR 2025

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu

Paper

GitHub

Website

ACL 2025

ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining

Xiao Yu*, Ruize Xu*, Chengyuan Xue*, Jinzhong Zhang, Xu Ma, Zhou Yu

Paper

GitHub