Zhuoyun Du is building
autonomous agents.

Master's Student, Computer Science @ Zhejiang University
LLM Algorithm Intern @ ByteDance

Research Focus Designing LLM-based autonomous agents that collaborate effectively to tackle complex tasks (software development, self-evolution, and latent-space reasoning).
Email CV Google Scholar GitHub Blog LinkedIn
Zhuoyun Du
I am a second-year master's student in Computer Science at Zhejiang University, working with Prof. Wei Chen at ZJUVAI. I am also an LLM Algorithm Intern at ByteDance, following internships at Alibaba and Tsinghua University.
Prospective PhD programs: Seeking Ph.D. positions for Fall 2027. Open to collaborations.
Prospective interns: Seeking Research Interns for LLMs & Agents. Email me.
News
Apr 2026
Three papers have been accepted to ACL 2026! Looking forward to see you in San Diego this July.
Selected Publications

(* denotes equal contribution)

Communication in Latent Space

Enabling Agents to Communicate Entirely in Latent Space.

DATE
VENUE
2026
ACL
Read paper → Code

Agent Coevolution

LLMs Can Simulate Standardized Patients via Agent Coevolution.

DATE
VENUE
2025
ACL
Read paper → Code

Cross-Team Orchestration

Multi-Agent Collaboration via Cross-Team Orchestration.

DATE
VENUE
2025
ACL
Read paper → Code
Learning to Evolve
A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization.
Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng.
ACL 2026.
Scaling Collaboration
Scaling Large-Language-Model-based Multi-Agent Collaboration.
Chen Qian*, Zihao Xie*, Yifei Wang*, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun.
ICLR 2025.
Paper Code
Information Asymmetry
Autonomous Agents for Collaborative Task under Information Asymmetry.
Wei Liu*, Chenxi Wang*, Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian.
NeurIPS 2024.
Paper Code
Experience
ByteDance
LLM Algorithm Intern (Jindouyun Talent Program) · Mar 2026 – Present
Focusing on LLM post-training (CT, SFT, RLHF/DPO) and constrained reinforcement learning in complex interactive environments. Researching preference alignment and multi-agent frameworks to tackle hallucination control, reward hacking, and policy compliance in high-stakes game-theoretic scenarios.
Alibaba Group
Research Intern @ Taotian Future Living Lab · Jan 2025 – Mar 2026
Spearheaded research on novel multi-agent collaborative paradigms, emphasizing latent space reasoning and communication efficiency. Designed and optimized Supervised Fine-Tuning (SFT) pipelines to substantially enhance LLM reasoning capabilities and task-solving performance in complex scenarios.
Tsinghua University
Research Assistant @ THUNLP · Nov 2023 – Aug 2024
Contributed to the ChatDev project and related studies with 32k stars on LLM-based multi-agent systems (especially Croto & MacNet), focusing on cross-agent and cross-team collaboration.
Featured Project

ChatDev & Croto

Pioneering LLM-based multi-agent collaboration. Actively contributed to the development and served as the leader for the Croto branch.

32,000+ Stars on GitHub. Featured by Andrew Ng & DeepMind.

View on GitHub → Read Paper
Multi-Agent E-book
A comprehensive collection of research papers on LLM-based multi-agent systems presented in an interactive e-book format. Organizes cutting-edge research into task-solving-oriented and social-simulation-oriented systems.
Website Dataset
Awards & Honors
2025
National Scholarship (TOP 0.2%)
Outstanding Student Scholarship
2024
First-Class Scholarship (Outstanding Graduate Student Award)
2022 – 2023
Second-Class Scholarship
Academic Service
Reviewer / PC
NeurIPS 2025, ICLR 2026
Beyond research, I enjoy soccer, fencing, snowboarding, billiards, playing the piano, photography, and physics.
Visit my personal blog. Last updated: March 2026.
© 2026 Zhuoyun Du. Hangzhou, China.
Weather: Loading...