Zhuangzhuang He

I received my M.S. in Computer Science and Technology from Hefei University of Technology in 2025, and my B.S. in the same major from Anhui Agricultural University in 2022. I visited the Information Retrieval Group during the summer of 2023.

I have all in LLM. My research interests covers a wide range of topics related to large language models, information retrieval:

  • LLM Enhancement: Reasoning, Agent;
  • LLM Applications: Science, OS-World.
I firmly believe that LLM are the most powerful tool for personal enhancement, and I am also dedicated to bringing the benefits of LLM to the world. Wechat: Stay-Aliving.

心似白云常自在， 亦如流水任东西。

Email  /  Google Scholar  /  Github  /  Twitter  

Papers

[1] From Language Model to Capable Agent: A Survey of Agent Training Frontiers [Repo]
Zhuangzhuang He, Haoyue Bai, Kaiyu Zhou, Yonghui Yang
arXiv 2025, Keep Updating.
[2] Double Correction Framework for Denoising Recommendation [Code]
Zhuangzhuang He*, Yifan Wang*, Yonghui Yang, Peijie Sun, Le Wu, Haoyue Bai, Jinqi Gong, Richang Hong, Min Zhang
KDD 2024, Oral Presentation.
Miscellaneous

⭐️ GitHub Stars   🚀 Awesome-RL-based-LLM-Reasoning
A curated list of resources for Reinforcement Learning (RL) based Large Language Model (LLM) reasoning.

⭐️ GitHub Stars   📚 Awesome-Agent-Training
A curated list of resources for agent training methods and techniques.

⭐️ GitHub Stars   🍳 The Simplest LLM-based Agent
Single-agent and multi-agent communication, implementing functions such as memory, planning, and function calling.