Tianyi Xu

xut2@oregonstate.edu

prof_pic.jpg

School of EECS, Oregon State University

Corvallis, OR 97331

I’m Tianyi Xu, a first-year Ph.D. student in Computer Science at Oregon State University, advised by Prof. Huazheng Wang. I graduated from the University of Wisconsin–Madison with a B.S. in Computer Science, Data Science, and Mathematics, where I worked with Prof. Junjie Hu. I also worked closely with Shaobo Wang and Prof. Linfeng Zhang at Shanghai Jiao Tong University, and Prof. Claudia Solís-Lemus at UW–Madison.

Research interests. I develop efficient and adaptive methods for AI agents, spanning multi-agent systems, test-time training and adaptation, self-evolution, and data-centric AI, where capability, reliability, and compute efficiency must be jointly optimized.

selected publications

  1. ICML (Oral)
    opus.png
    OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
    Shaobo Wang*, Xuan Ouyang*, Tianyi Xu*, Yuzheng Hu, Jialin Liu, Guo Chen, Tianyu Zhang, Junhao Zheng, Kexin Yang, Xingzhang Ren, Dayiheng Liu, and Linfeng Zhang
    In International Conference on Machine Learning (ICML), May 2026
    Oral arXiv Blog
  2. arXiv
    evopool.jpg
    EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
    Tianyi Xu, Yaolun Zhang, Xuan Ouyang, and Huazheng Wang
    Jun 2026
    Under review
    arXiv
  3. arXiv
    evochamber.png
    EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
    Yaolun Zhang*, Tianyi Xu*, Shengyu Dai, Zhenwen Shao, Qingyun Wu, and Huazheng Wang
    Apr 2026
    Under review
    arXiv