Zhouzhou Shen

Zhejiang, China

Hi! I’m Zhouzhou Shen, a master’s student at AI4GC Lab, Zhejiang University, advised by Prof. Shengyu Zhang.

My research focuses on computer-using agents. For example, I study web agents that use world models to anticipate, verify, and correct their actions, making interactive automation more reliable in real web environments.

Education

M.S. in Computer Technology, Zhejiang University, 2025–present
B.S. in Computer Science and Technology, Southeast University, 2021–2025

Research Interests

Computer-Using Agents — for example, web agents that reason about interactive environments and recover from incorrect or uncertain actions.

Open-Source Projects

Video Production Buddy — an open-source AI video production assistant that turns general-purpose agents into video production experts, with brief clarification, proposal gates, asset generation, composition, and review before expensive generation runs. GitHub

selected publications

World-Model-Augmented Web Agents with Action Correction

Zhouzhou Shen^*, Xueyu Hu^*, Xiyun Li, Tianqing Fang, Juncheng Li, and Shengyu Zhang

arXiv, 2026

arXiv Bib

@article{shen2026worldmodel,
  title = {World-Model-Augmented Web Agents with Action Correction},
  author = {Shen, Zhouzhou and Hu, Xueyu and Li, Xiyun and Fang, Tianqing and Li, Juncheng and Zhang, Shengyu},
  journal = {arXiv},
  year = {2026},
  url = {https://arxiv.org/abs/2602.15384},
}

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference

Kunxi Li^*, Zhonghua Jiang^*, Zhouzhou Shen, Zhaode Wang, Chengfei Lv, Shengyu Zhang, Fan Wu, and Fei Wu

In ACL, 2025

DOI Bib

@inproceedings{li2025madakv,
  title = {{MadaKV}: Adaptive Modality-Perception {KV} Cache Eviction for Efficient Multimodal Long-Context Inference},
  author = {Li, Kunxi and Jiang, Zhonghua and Shen, Zhouzhou and Wang, Zhaode and Lv, Chengfei and Zhang, Shengyu and Wu, Fan and Wu, Fei},
  booktitle = {ACL},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.652},
  url = {https://doi.org/10.18653/v1/2025.acl-long.652},
}