About Me

Open to internship Open to collaboration

I am currently a PhD student at Institute of Automation, Chinese Academy of Sciences, advised by Prof. Guoliang Fan. I obtained my B.Eng. (2022) at Wuhan University, advised by Prof. Wen Yang. Currently, I am jointly trained at Zhongguancun Academy in Beijing under the supervision of Prof. Chao Yu, and collaborating with Infinigence AI on developing and maintaining the RLinf framework.

Previously I was a research intern at Microsoft Research Asia (MSRA), where I worked on multi-agent reinforcement learning under the guidance of mentor Xianliang Yang and Dr. Lei Song.

My current research interests include embodied intelligence, multi-agent reinforcement learning, and LLM for RL.

Research Focus

Embodied Intelligence

Building intelligent agents that interact with physical environments through perception, reasoning, and action.

Primary Focus

LLM for RL

Leveraging large language models to enhance reinforcement learning through semantic understanding, reasoning, and decision-making.

Active Research

Multi-Agent RL

Designing efficient algorithms for cooperative and competitive multi-agent reinforcement learning scenarios.

Core Expertise

Publications

2026 ▼
Peak-Return Greedy Slicing: Subtrajectory Selection for Transformer-based Offline RL
Zhiwei Xu, Miduo Cui, Dapeng Li, Zhihao Liu, Haifeng Zhang, Hangyu Mao, Guoliang Fan, Bin Zhang
ICLR 2026
2025 ▼
RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
Chao Yu, Yuanqing Wang, Zhen Guo, Hao Lin, Si Xu, Hongzhi Zang, Quanlu Zhang, Yongji Wu, Chunyang Zhu, Junhao Hu, et al.
arXiv preprint
πRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Kang Chen, Zhihao Liu*, Tonghe Zhang, Zhen Guo, Si Xu, Hao Lin, Hongzhi Zang, Xiang Li, Quanlu Zhang, Zhaofei Yu, et al.
arXiv preprint · * Equal contribution
RLinf-VLA: A Unified and Efficient Framework for VLA + RL Training
Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, et al.
arXiv preprint
2024 ▼
2023 ▼
2021 ▼

Experience

Microsoft Research Asia (MSRA)
Research Intern · Machine Learning Group · Feb 2023 – Jun 2024