😊 About Me

My research interests lie in agents based on large models (LLMs/MLMs). Specifically, I am interested in:

• The integration of LMs with APIs (tools).
• Retrieval augmented generation.
• Multi-Agent Scaling.

Recently, I aim to explore the integration of LLM inference scaling with Tools.

My research group primarily focuses on system software, including machine learning systems, web systems, software engineering, and etc. However, during my second year of PhD studies, I discovered a greater interest in AI, so my current focus is primarily on AI :-).

📝 Publications

• Z. Tao, …,H. Shen, et al. “WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization”, arXiv (arXiv’25).
  • https://arxiv.org/abs/2507.15061
• Z. Shao*, H. Shen*, et al. “Grounding AI Explanations in Experience: A Reflective Cognitive Architecture for Clinical Decision Support”, arXiv (arXiv’25).
  • https://arxiv.org/abs/2509.21266
• H. Shen*, H. Yan*, et al. “RAGSynth: Synthetic Data for Robust and Faithful RAG Component Optimization”, arXiv (arXiv’25).
  • http://arxiv.org/abs/2505.10989
• T. Guo*, H. Shen*, et al. “MASS: Multi-Agent Simulation Scaling for Portfolio Construction”, arXiv, (arXiv’25).
  • https://arxiv.org/abs/2505.10278.
• Q. Yang, W. B, H.Shen et al. “PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels”, arXiv (arXiv’25).
  • https://arxiv.org/abs/2504.16419.
• Z. Chen, Y. Ma, H.Shen et al. “WeInfer: Unleashing the Power of WebGPU on LLM Inference in Web Browsers”, the Web Conference (WWW’25).
  • https://openreview.net/forum?id=Qu2itILaoZ#discussion.
• H. Shen, Y. Li et al. “Shortcutsbench: A large-scale real-world benchmark for API-based agents” the International Conference on Learning Representations (ICLR’25).
  • https://openreview.net/forum?id=kKILfPkhSz
  • https://arxiv.org/abs/2407.00132
  • Project Link
• M. Liu, H.Shen et al. “WebAssembly for Container Runtime: Are We There Yet?” Transactions on Software Engineering Methodology (TOSEM’24).
  • https://dl.acm.org/doi/10.1145/3712197

• H. Shen, Y. Ma et al. “Adpal: Automatic detection of troubled users in online service systems via page access logs”, IEEE International Conference on Web Services (ICWS’23).

  • https://doi.org/10.1109/ICWS60048.2023.00082
  • https://github.com/eachsheep/abnormaldetection

📖 Experience

• Intern, with Alibab Tongyi DeepResearch Group (2025.06 ~ now)
  • WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization.
  • Tongyi DeepResearch https://github.com/Alibaba-nlp/DeepResearch, which has gained over 10k Star⭐ and was trending on GitHub.
  • TBD.
• Intern, with Miracleplus \& with Hang Yan in Shanghai AI Lab. (2024.11 - 2025.05)
• Outstanding Research Award, Peking University (2022-2023)

• Ph.D. Candidate in Computer Science and Technology, School of Computer Science at Peking University (2022.09 - now)

  • Ph.D. comprehensive exam: LLM, MLM, and LLM-based agent

• Researcher, Alibaba Innovative Researcher in Technical & Quality at Fliggy, Alibaba (2022.08 - 2022.10)

  • Research topic: Anomaly detection using page access logs
• National Scholarship, First Class Scholarship, and WU Yajun Scholarship, Northwestern Polytechnical University (2019 ~ 2021)
• B.Sc. in Computer Science and Technology, School of Computer Science at Northwestern Polytechnical University (2018.09 - 2022.07)

📫 Correspondence

• 📧 hyshen@stu.pku.edu.cn
• 🐙 https://github.com/eachsheep
• 🌐 https://eachsheep.space