Publications

A record of collaborative work.

Peer-reviewed papers and preprints, organized by year. * denotes equal contribution.

Full list also on Google Scholar.

2026 1 paper

  1. LLM Reasoning & Agency14th ICLR, 2026

    SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

    Yuqian Fu, Tinghong Chen, Jiajun Chai, Xihuai Wang, Songjun Tu, Guojun Yin, Wei Lin, Qichao Zhang, Yuanheng Zhu, and Dongbin Zhao

    arXiv PDF

2025 2 papers

  1. LLM Reasoning & Agency63rd ACL, 2025

    Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration

    Shao Zhang*, Xihuai Wang*, Wenhao Zhang, Chaoran Li, Junru Song, Tingyu Li, Lin Qiu, Xuezhi Cao, Xunliang Cai, Wen Yao, Weinan Zhang, Xinbing Wang, and Ying Wen

    arXiv PDF Code
  2. MARL Efficiency24th AAMAS, 2025

    PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning

    Kun Hu, Muning Wen, Xihuai Wang, Shao Zhang, Yiwei Shi, Minne Li, Minglong Li, and Ying Wen

    arXiv PDF Code

2024 2 papers

  1. LLM Reasoning & AgencyPreprint Under Review, 2024

    Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task

    Shao Zhang*, Xihuai Wang*, Wenhao Zhang, Yongshan Chen, Landi Gao, Dakuo Wang, Weinan Zhang, Xinbing Wang, and Ying Wen

    arXiv PDF
  2. MARL Generalization38th NeurIPS, 2024

    ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination

    Xihuai Wang, Shao Zhang, Wenhao Zhang, Wentao Dong, Jingxiao Chen, Ying Wen, and Weinan Zhang

    arXiv PDF Code

2023 1 paper

  1. MARL Efficiency11th ICLR, 2023

    Order Matters: Agent-by-agent Policy Optimization

    Xihuai Wang, Zheng Tian, Ziyu Wan, Ying Wen, Jun Wang, and Weinan Zhang

    OpenReview PDF Code

2022 1 paper

  1. MARL EfficiencyarXiv preprint arXiv:2203.10603, 2022

    Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects

    Xihuai Wang, Zhicheng Zhang, and Weinan Zhang

    PDF

2021 1 paper

  1. MARL Efficiency30th IJCAI, 2021

    Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

    Weinan Zhang, Xihuai Wang, Jian Shen, and Ming Zhou

    PDF Code