Yunzhan Li

Publications

* indicates equal contribution.

Preprints

  • Teaser figure for Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies

    Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies

    Zhuoran Li, Yunzhan Li, Xun Wang, Yihan Du, and Longbo Huang.

    arXiv preprint arXiv:2610.01882, 2026.

    We propose an Online MARL framework via one-step Flow models (OMAF) that combines expressive generative policies with efficient one-step action generation, which achieves superior policy performance while unlocking expressive and highly efficient policy learning for online MARL.

    arXiv