Tao Xiong

AI4GC Lab

Tao Xiong

GUI/CLI AgentsReward ModelingMLLM Reasoning
Google ScholarGitHub

About Me

Hi! I'm Tao Xiong (熊涛), a master's student at AI4GC Lab, Zhejiang University, advised by Prof. Shengyu Zhang.

My research focuses on building reliable GUI agents that can operate real software through CLI and GUI interfaces, with a particular interest in reward modeling for improving agent decision-making and multimodal LLM reasoning.

Feel free to reach out for collaboration!

Research Interests

  • GUI Agents — Building and evaluating agents that interact with graphical user interfaces across platforms for complex, long-horizon tasks.
  • Reward Modeling — Designing reward models to support benchmark evaluation, trajectory selection, as well as provide reward signals for reinforcement learning.
  • MLLM Reasoning — Enhancing multimodal large language models' reasoning and generalization capabilities.

Education

  • 2025 – present · M.S. in Artificial Intelligence, Zhejiang University
  • 2021 – 2025 · B.S. in Computer Science and Technology, Dalian University of Technology

Selected Papers

arXiv2025

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies

Tao Xiong, Xavier Hu, Wenyan Fan, Shengyu Zhang✉

Paper

ACL2025

Oral

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang✉, Fei Wu

PaperProject485

Internships

  • 2026.05 – present · Xiaomi, Xiao Ai Plus, Beijing
  • 2025.10 – 2026.05 · Xiaomi, MiLM Plus, Beijing