Xiangyu Liu

2104 Brendan Iribe Center

College Park, Maryland 20740

I am a fourth-year PhD student in Computer Science at the University of Maryland, College Park (UMD) since 2021, working under the guidance of Prof. Kaiqing Zhang. I have also had the privilege of working with Prof. Furong Huang. Prior to this, I completed my undergraduate studies in Computer Science at Shanghai Jiao Tong University (SJTU) from 2017 to 2021, where I conducted my bachelor thesis research with Prof. Ying Wen.

My research focuses on the foundational aspects of (multi-agent) reinforcement learning (RL), particularly on game-theoretical/strategic (NeurIPS 2021, ICML 2023) and partially observable settings (NeurIPS 2024), as well as their applications on adversarially robust RL (ICLR 2024).

More recently, I have expanded my research to explore (multi-)large language model (LLM) agents interactions (ICLR 2025), leveraging techniques from game theory and online learning.

News

Apr 18, 2025	Gave an invited talk at UVA RL Meetup.
Jan 22, 2025	One paper accepted to ICLR 2025 on LLM agents.
Sep 25, 2024	One paper accepted to NeurIPS 2024 on partially observable RL with privileged information.
Mar 24, 2024	Gave a talk at 2024 INFORMS Optimization Society Conference (IOS 2024) on partially obseravble multi-agent RL at Houston, Texas.
Jan 16, 2024	Three papers accepted to ICLR 2024 including one spotlight.

Selected publications

* denotes equal contribution, † denotes alphabetical order.

NeurIPS 2021

Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

Xiangyu Liu, Hangtian Jia, Ying Wen, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu, and Yaodong Yang

Advances in Neural Information Processing Systems, 2021

Code Website
ICML 2023

Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing

Xiangyu Liu, and Kaiqing Zhang

In International Conference on Machine Learning, 2023
Extended version accepted to SIAM Journal on Control and Optimization (SICON) under revision

arXiv
NeurIPS 2024

Provable Partially Observable Reinforcement Learning with Privileged Information

Yang Cai^†, Xiangyu Liu^†, Argyris Oikonomou^†, and Kaiqing Zhang^†

In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
A shorter version also presented at ICML 2024 ARLET workshop.

arXiv
ICLR 2024 (spotlight)

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Xiangyu Liu^*, Chenghao Deng^*, Yanchao Sun, Yongyuan Liang, and Furong Huang

In The Twelfth International Conference on Learning Representations, 2024

arXiv Code Website
ICLR 2025

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

Chanwoo Park^*, Xiangyu Liu^*, Asuman Ozdaglar, and Kaiqing Zhang

In The Thirteenth International Conference on Learning Representations, 2025

arXiv

Talks

Talk at the 2024 INFORMS Optimization Society Conference (IOS 2024) on partially observable multi-agent RL, Houston, Texas, 2024
Contributed talk at the TSRML workshop of NeurIPS 2022 on adversarial policies in competitive games, 2022
Talk at RLChina on unifying diversity in open-ended learning for zero-sum games, China, 2021

Awards

Outstanding Paper Award, Trustworthy and Socially Responsible Machine Learning (TSRML) workshop, NeurIPS 2022
Dean's Fellowship, UMD, 2021
National Scholarship, China, 2018 & 2019

Service

Reviewer for NeurIPS 2024-2025, ICLR 2025, ICML 2025, AISTATS 2025, UAI 2024-2025, AAMAS 2025, CDC 2025
Graduate lecturer at summer AI camps for K12 students (2023, 2024), teaching multi-agent RL.