Yang Li

Tenure-Track Assistant Professor @ SJTU | Advisor @ Shanghai AI Lab | Multi-Agent Systems · Embodied AI · AI for Science

yang_bio.png

AP, John Hopcroft Center for Computer Science

Shanghai Jiao Tong University

Advisor, Physical Intelligence Center

Shanghai AI Laboratory

✉️ yang.li.cs at sjtu dot edu dot cn

About Me

I am a Tenure-Track Assistant Professor (长聘教轨助理教授) at the John Hopcroft Center for Computer Science, Shanghai Jiao Tong University. I also serve as an Advisor to the Physical Intelligence Center at Shanghai AI Laboratory. My research lies at the intersection of embodied AI, multi-agent systems, and AI for science. I study how embodied agents can learn to collaborate, adapt to unseen environments and teammates, and operate persistently in the physical world. My long-term goal is to build scalable and trustworthy teams of embodied agents that can reason, coordinate, and accelerate scientific discovery through autonomous experimentation.

Before joining SJTU, I was a Research Scientist on the Agent Team at Huawei’s London Research Center. I received my Ph.D. in Computer Science from the University of Manchester, supervised by Dr. Wei Pan and co-supervised by Prof. Angelo Cangelosi. I also hold an M.Eng. in Information and Communication Engineering from the University of Chinese Academy of Sciences, with joint training at ShanghaiTech University under Prof. Jun Wang and Prof. Yang Yang, and a B.Eng. in Digital Media Technology from Dalian University of Technology.

Join Us

My group at SJTU continuously welcomes highly motivated Ph.D. students, research assistants, and interns, as well as undergraduate and master’s students interested in gaining research experience. In addition, our team at the Physical Intelligence Center, Shanghai AI Laboratory, is continuously recruiting full-time researchers, engineers, and interns. Our current openings cover embodied AI, multi-agent and multi-robot systems, AI for science, AI for nuclear science, and self-driving laboratories.

If you are interested, please email me at yang.li.cs at sjtu dot edu dot cn with your CV and a brief description of your research interests. Student applicants should also include their transcripts.

News

Aug 06, 2026 New paper: “SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution” (Corresponding Author). SkillTV-Bench evaluates whether LLM- and agent-based judges can verify complete skill-augmented agent executions, while SkillTV-Evolve automatically refines a reusable JudgeSkill for more reliable trajectory verification and rollout selection. arXiv · Code
Aug 03, 2026 Two new papers are available. “CoNav-UAV” (Corresponding Author) models cooperative dual-altitude aerial navigation as a Stackelberg game, coupling a high-altitude VLM leader with a low-altitude control follower (arXiv). “DF³” (Corresponding Author) forecasts future states entirely within a frozen vision encoder, removing heavy decoders for efficient autonomous navigation (arXiv).
Jul 24, 2026 New preprint: “InternLab: A Governed Network of Physically Intelligent Autonomous Laboratories for Open-world Scientific Discovery” (First Author). InternLab proposes a governed network that connects physically intelligent autonomous laboratories, enabling coordinated and accountable open-world scientific discovery across distributed physical labs. DOI
Jul 06, 2026 New paper: “Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales” (First Author). We formulate open adaptive multi-robot teaming and introduce HOLA, enabling drone and quadruped teams to coordinate with unseen partners, in unseen environments, and at varying team scales, with zero-shot transfer to physical robots. arXiv
Jun 29, 2026 New paper: “Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration.” Clarus turns autonomous research from a closed workflow into an open, auditable, attributable, and resource-aware collaboration network connecting agents, researchers, and physical laboratories. arXiv · Project

Latest Posts

Jul 18, 2026 Embodied AI and Autonomous Laboratories Tutorial
May 08, 2026 World Model：从强化学习到具身智能的完整入门

Selected Publications

  1. Preprint
    InternLab: A Governed Network of Physically Intelligent Autonomous Laboratories for Open-world Scientific Discovery
    Yang Li, Ming Zhou, Dongzhan Zhou, and 51 more authors
    Unpublished, 2026
  2. arXiv
    Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales
    Yang Li, Feng Xue, Fan Mo, and 6 more authors
    arXiv preprint arXiv:2607.04972, 2026
    arXiv PDF
  3. arXiv
    Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
    Yang Li, Zhiyuan He, Yuxuan Huang, and 5 more authors
    arXiv preprint arXiv:2511.23262, 2025
    arXiv PDF
  4. arXiv
    AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit
    Yang Li, Junfan Chen, Feng Xue, and 5 more authors
    arXiv preprint arXiv:2502.09762, 2025
    arXiv PDF Website
  5. Under Review
    esa.png
    Position: Autonomous Scientific Discovery Needs Embodied Experimentation with Learnability
    Yihang Chen, Zhongwei Yu, Yang Li, and 4 more authors
    TechRxiv, 2026
    PDF
  6. NeurIPS
    Aligning Individual and Collective Objectives in Multi-Agent Cooperation
    Yang Li, Wenhao Zhang, Jianhong Wang, and 4 more authors
    arXiv preprint arXiv:2402.12416, 2024
    PDF
  7. JAIR
    cole-sys.png
    Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination
    Yang Li, Shao Zhang, Jichen Sun, and 5 more authors
    Journal of Artificial Intelligence Research, 2024
    PDF Code Website
  8. Under Review
    hola-demo.gif
    HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit
    Yang Li, Dengyu Zhang, Junfan Chen, and 3 more authors
    2024
    Website
  9. ICML
    cole-demo.gif
    Cooperative Open-ended Learning Framework for Zero-shot Coordination
    Yang Li, Shao Zhang, Jichen Sun, and 4 more authors
    In Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20470-20484, 2023. , 2023
    PDF Code Website
  10. TMLR
    jiangjun.JPG
    JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games
    Yang Li, Kun Xiong, Yingping Zhang, and 6 more authors
    Transactions on Machine Learning Research, 2023
    PDF Code Website
  11. IEEE TMC
    s2mafenn.JPG
    Self-Supervised MAFENN for Classifying Low-labeled Distorted Images over Mobile Fading Channels
    Yang Li, Fanglei Sun, Jingchen Hu, and 8 more authors
    IEEE Transactions on Mobile Computing, 2023
    PDF Website
  12. TASLP
    Cross-Utterance Conditioned VAE for Speech Generation
    Yang Li, Cheng Yu, Guangzhi Sun, and 7 more authors
    In , 2024
  13. ACL
    cucvae.JPG
    Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech
    Yang Li, Cheng Yu, Guangzhi Sun, and 6 more authors
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2022
    PDF

Selected Co-authored Publications

  1. arXiv
    SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution
    Zhi Han, Chenxi Zeng, Liuhaichen Yang, and 3 more authors
    arXiv preprint arXiv:2608.05573, 2026
    arXiv PDF Code
  2. arXiv
    Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
    Zihan Guo, Zeyi Chen, Zhiyu Chen, and 15 more authors
    arXiv preprint arXiv:2606.30246, 2026
    arXiv PDF Website
  3. arXiv
    CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning
    Junru Song, Wenhao Zhang, Yang Yang, and 7 more authors
    arXiv preprint arXiv:2608.01802, 2026
    arXiv PDF
  4. arXiv
    DF^3: World Modeling via Decoder-Free Feature Forecasting in Autonomous Navigation
    Jiaming Chen, Guoan Xu, Aoshen Huang, and 3 more authors
    arXiv preprint arXiv:2608.02428, 2026
    arXiv PDF
  5. arXiv
    PEPA: a Persistently Autonomous Embodied Agent with Personalities
    Kaige Liu, Yang Li, Lijun Zhu, and 1 more author
    arXiv preprint arXiv:2603.00117, 2026
    arXiv PDF Website
  6. IEEE RAL
    VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation
    Jiaming Chen, Yiyu Jiang, Aoshen Huang, and 2 more authors
    IEEE Robotics and Automation Letters, 2026
    arXiv PDF Website
  7. ICML
    ciao-demo.gif
    Open Ad Hoc Teamwork with Cooperative Game Theory
    Jianhong Wang, Yang Li, Yuan Zhang, and 2 more authors
    arXiv preprint arXiv:2402.15259, 2024
    PDF Code Website
  8. ICML
    A2PR.JPG
    Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
    Tenglong Liu, Yang Li, Yixing Lan, and 3 more authors
    arXiv preprint arXiv:2405.19909, 2024
    PDF Website
  9. ICLR
    LIGS.JPG
    Ligs: Learnable intrinsic-reward generation selection for multi-agent learning
    David Henry Mguni, Taher Jafferjee, Jianhong Wang, and 7 more authors
    arXiv preprint arXiv:2112.02618, 2021
    PDF
  10. Under Review
    LLaMAC.JPG
    Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
    Bin Zhang, Hangyu Mao, Jingqing Ruan, and 8 more authors
    arXiv preprint arXiv:2311.13884, 2023
    PDF
  11. IEEE TWC
    Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications
    Fanglei Sun, Yang Li, Ying Wen, and 4 more authors
    IEEE Transactions on Wireless Communications, 2022
    PDF