I am an undergraduate student majoring in Artificial Intelligence at the School of Intelligence Science and Technology, Nanjing University (NJU).
My research interests lie in AI agents, large language models, multimodal representation learning, and reliable evaluation. I am particularly interested in building agentic systems that can perceive, reason, and generalize in open and changing environments.
At NJU, I am advised by Prof. Lanzhe Guo in the LAMDA Lab and Prof. Kai Zhang in the CVL Lab. I also work with Prof. Tao Yu in the XLang Lab at The University of Hong Kong on OSWorld 2.0, a benchmark for evaluating long horizon computer use agents.
๐ If youโre interested in my research or just want to chat, feel free to reach out by email or .
๐ฅ News
- 2026.05: ย ๐๐ Our paper RideJudge is accepted by KDD 2026!
- 2026.05: ย ๐๐ Our paper OpenAgent is accepted by ICML 2026!
- 2025.07: ย ๐๐ Our work NesyGeo is accepted by AI4Math@ICML25!
๐ Publications
* Equal contribution.

OSWorld 2.0: Benchmarking Computer-Use Agents on Long-Horizon Real-World Tasks
Mengqi Yuan*, Zilong Zhou*, Xinzhuang Xiong*, Weiming Wu, Jiayang Sun, Jiamin Song, Kaiqian Cui, Bowen Wang, Haoyuan Wu, Yitong Li, Dunjie Lu, Haikong Lu, Qi Zhen, Xinyuan Wang, Jiaqi Deng, Yuhao Yang, Cheng Chen, Boyuan Zheng, Alex Su, Xiao Yu, Hao Zou, Saaket Agashe, Xing Han Lu, Manpreet Kaur, Zhengyang Qi, Vincent Sunn Chen, Frederic Sala, Dayiheng Liu, Junyang Lin, Zhou Yu, Yu Su, Siva Reddy, Xin Eric Wang, Peng Qi, Tianbao Xie, Tao Yu
Paper | Project | Code | GitHub stars: loadingโฆ
OSWorld 2.0 Hugging Face assets, file cache, and trajectories have been downloaded over 300K times.

Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
Weiming Wu*, Song-Lin Lv*, Rui Zhu, Zi-Jian Cheng, Lan-Zhe Guo

A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication
Weiming Wu*, Zi-Jian Cheng*, Jie Meng, Peng Zhen, Shan Huang, Qun Li, Guobin Wu, Lan-Zhe Guo

NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data Generation
Weiming Wu, Jin Ye, Zi-Kang Wang, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo

On Path to Multimodal Generalist: General-Level and General-Bench
Hao Fei*, Yuan Zhou*, Juncheng Li*, Xiangtai Li*, Qingshan Xu*, Bobo Li*, Shengqiong Wu*, Yaoting Wang, Junbao Zhou, Jiahao Meng, Qingyu Shi, Zhiyuan Zhou, Liangtao Shi, Minghe Gao, Daoan Zhang, Zhiqi Ge, Weiming Wu, Siliang Tang, Kaihang Pan, Yaobo Ye, Haobo Yuan, Tao Zhang, Tianjie Ju, Zixiang Meng, Shilin Xu, Liyu Jia, Wentao Hu, Meng Luo, Jiebo Luo, Tat-Seng Chua, Shuicheng Yan, Hanwang Zhang
Paper | Project | Benchmark | ้ๅญไฝ | Citations: 108
General-Bench Open Set, Close Set, and Scoped Close Set have been downloaded over 360K times on Hugging Face.

KDARO: Knowledge-Data Automated Rule Optimization for Liability Adjudication Task
Zi-Jian Cheng*, Weiming Wu*, Jie Meng, Zhen Peng, Shan Huang, Qun Li, Guobin Wu, Lan-Zhe Guo

MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?
Ziqiao Shang*, Lingyue Ge*, Zi-Jian Cheng, Shi-Yu Tian, Zhenyu Huang, Wenbo Fu, Weiming Wu, Yang Chen, Xiangwen Zhang, Yulan Hu, Bin Liu, Yu-Feng Li, Lan-Zhe Guo
๐ Selected Honors and Awards
- 2025: National Scholarship (Top 0.2%, Highest Honor for undergraduates in China)
- 2024: Nanjing University RuLi Scholarship
๐ Educations
- 2023.09 - now, School of Intelligence Science and Technology, Nanjing University
๐ผ Experience
- 2026.02 - now, Research Assistant, XLANG Lab, The University of Hong Kong
- 2025.07 - 2026.04, Research Intern, MPT Department, Didiglobal, Beijing, China
- 2024.10 - now, Research Assistant, Lamda-12 Lab, Nanjing University
๐โโ๏ธ Services
- Reviewer: ECAIโ25, IJCNNโ26, ICMLโ25 Workshop@AI4Math
- Teaching Assistant: 2025 fall Introduction to AI at NJU IS