I am an incoming MPhil in HKUST CSE, supervised by Prof. Junxian He. I received my B.S. degree from the CKC honor college at Zhejiang University in 2025, majoring in computer science. During my undergraduate years, I collaborated with Dr. Jie Fu and Prof. Ningyu Zhang.

After exploring several research areas, my interests have gradually converged on building general intelligent agents (AGI), with two key directions:

Reasoning — particularly, how reinforcement learning can shape and enhance reasoning capabilities
Tool-using agents — developing improved algorithms and challenging datasets to strengthen models’ ability to invoke tools and solve real-world tasks

I am open to any collaboration😊

Publications

(* denotes co-first authors)

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Junlong Li*, Wenshuo Zhao*, Jian Zhao*, Weihao Zeng*, Haoze Wu*, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu, Junteng Liu, Zhaochen Su, Yiyang Guo, Fan Zhou, Lueyang Zhang, Juan Michelini, Xingyao Wang, Xiang Yue, Shuyan Zhou, Graham Neubig, Junxian He
Arxiv, 2025 | PDF | Code | Page | Dataset

Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions

Haoze Wu*, Cheng Wang*, Wenshuo Zhao, Junxian He
MATH-AI@NeurIPS 2025 | PDF | Code

Recode: Updating code api knowledge with reinforcement learning

Haoze Wu, Yunzhi Yao, Wenhao Yu, Ningyu Zhang
AAAI 2026 | PDF | Code | Dataset

GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory

Haoze Wu*, Zihan Qiu*, Zili Wang, Hang Zhao, Jie Fu
Arxiv, 2024 | PDF | Code

Educations

2021.09 - 2025.06, B.S.@ZJU, Compter Science

Internships

2025.10 - present, Huawei Noah’s Ark Lab, Shenzhen.
2024.10 - 2025.01, Shanghai AI Lab, Shanghai.

Service

Reviewer: Math-AI@NeurIPS