About me
My name is Zhuoyun Du (杜卓耘). I am a first-year graduate student at Zhejiang University, majoring in Computer Science. My research interests encompass Artificial Intelligence, Natural Language Processing, Large Language Models, and Multi-agent Systems.
During my senior year of undergraduate studies, I served as a Research Assistant in the group of ChatDev 
at Tsinghua University, under the guidance of Prof. Zhiyuan Liu and Dr. Chen Qian from THUNLP at Tsinghua University.
My graduate advisor is Prof. Wei Chen from the ZJUVAI, State Key Lab of CAD&CG, Zhejiang University.
I have a passion for sharing blogs on my blog site, where I share my research learning, photography works, and daily life. Aside from research, I have a keen interest in sports such as soccer, fencing, and snowboarding. I am passionate about music and enjoy playing the piano and guitar (although I’m just a beginner). I also have a love for photography and reading.
Feel free to reach me at xiaodu.flying@gmail.com.
Research Intrest
LLM-based Agent🤖
I'm focused on developing LLM-based autonomous agents capable of effectively and efficiently tackling multi-step complexes. Previously, my focus was primarily on software development and story generation, but now I'm eager to explore broader applications. Particularly, I'm intrigued by the concept of LLM-based multi-agent systems。🎉 News
[2024.9.26] Our team’s paper Autonomous Agent for Collaborative Task under Information Asymmetry has been accepted to NeurIPS 2024 , congrats to Wei Liu, Chenxi Wang and all co-authors. 🥳
[2024.6.25] 🎉To foster development in LLM-powered multi-agent collaboration🤖🤖 and related fields, our team has curated a collection of seminal papers📄 presented in an interactive e-book📚 format. Explore the latest advancements and download the paper list here: ebook
[2024.6.21] 🎉Our work related to Agents for Collaborative Task under Information Asymmetry 👥 is available on arxiv:2406.14928
[2024.6.14] Our work related to multi-agent collaboration from the perspective of cross-team 🚩🚩 organization that breaks 🔨 the isolation nature of a single team has been released on arXiv:2406.08979 first.
[2024.6.12] Our work related to multi-agent collaboration studied the scaling law 🕸️ in multi-agent systems and our framework supporting various topologies and over a thousand agents🤖🤖 to collaborate for task resolution has been released on arXiv:2406.07155.
[2024.5.16] Our team’s two papers ChatDev and Experiential Co-learning have been accepted to ACL 2024, main conference, congrats to them. 🥳
📖 Publications
Author & Co-Author
Multi-Agent Software Development through Cross-Team Collaboration. In arXiv:2406.08979. Zhuoyun Du \(^\dagger\), Chen Qian \(^\dagger\), Wei Liu, Zihao Xie, Yifei Wang, Yufan Dang, Weize Chen, Cheng Yang.
Scaling Large-Language-Model-based Multi-Agent Collaboration. In arXiv:2406.07155. Chen Qian \(^\dagger\), Zihao Xie \(^\dagger\), Yifei Wang \(^\dagger\), Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun.
Autonomous Agents for Collaborative Task under Information Asymmetry. In Advances in Neural Information Processing Systems. Wei Liu \(^\dagger\), Chenxi Wang \(^\dagger\), Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian.
Highly related
Iterative Experience Refinement of Software-Developing Agents. In arXiv:2405.04219, 2024. Chen Qian \(^\dagger\), Jiahao Li \(^\dagger\), Yufan Dang, Wei Liu, YiFei Wang, Zihao Xie, Weize Chen, Cheng Yang, Yingli Zhang, Zhiyuan Liu, Maosong Sun.
Experiential Co-Learning of Software-Developing Agents. ACL 2024 main conference. Chen Qian \(^\dagger\), Yufan Dang \(^\dagger\), Jiahao Li, Wei Liu, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun.
Communicative Agents for Software Development. ACL 2024 main conference. Chen Qian, Xin Cong, Wei Liu, Cheng Yang, Weize Chen, Yusheng Su, Yufan Dang , Jiahao Li, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun.
\(\dagger\): Equal Contribution.
🐣 Research Experience
THUNLP Natural Language Processing Lab at Tsinghua University
Research Intern, Nov. 2023 – Aug. 2024
- Participating in the ChatDev project, maintaining the system, and adding new features. The focus of my research was on the cutting-edge field of improving the capabilities of multi-agent teams through cross-team collaboration.
🔍Old News🔮
[2024.5.6] Following our prior work on ECL, we’re excited to announce the publication of our team’s latest endeavor, Iterative Experience Refinement 💪 of Software-Developing Agents, available on arXiv:2405.04219.
[2024.1.25] Code and data 🔍 around Experiential Co-Learning of Software-Developing Agents has released in ECL in ChatDev.
[2023.12.29] Following ChatDev, our team has introduced Experiential Co-Learning🕵️, which extracts shortcut experiences from the behavioral trajectories of multiple agents on historical tasks. Utilizing retrieval-assisted mutual inference on unseen tasks, available on arxiv:2312.17025.
[2023.8.29] ChatDev has been open-sourced 🎉, and to date, it has already received
, which is truly exciting![2023.7.16] 🎉ChatDev is released on arxiv.org:2307.07924. It can be your Virtual Software Dream Team! ChatDev is redefining software development with a diverse team of AI-powered agents. Share your initial idea💭 and witness these agents cooperatively communicate💬 for software development.