Hongyi Du ☕️
Hongyi Du Hong-yee Du

Undergraduate Research Assistant

Blender Lab at UIUC

About Me

Hongyi Du is an undergraduate researcher in the Blender Lab and U Lab at the University of Illinois Urbana-Champaign. His work focuses on LLM multi-agent systems, multi-agent communication protocols, and self-evolving agent architectures. He is the first author of ProtocolBench (under review at ICLR 2026), which benchmarks LLM multi-agent communication protocols and introduces ProtocolRouter for dynamic protocol selection. He also co-develops open benchmarks such as MultiAgentBench (ACL 2025) and ModelingBench (EMNLP 2025), building reusable agent frameworks that integrate data, simulation, and evaluation at scale.

Download CV
Interests
  • LLM Multi-agent System
  • Self-evolving Agent Systems
  • LLM Tool Learning
Education

  • University of Illinois Urbana-Champaign

📚 My Research

I dive into the wild world of multi-agent LLMs and tool-powered reasoning, whipping up plug-and-play frameworks that let data, simulations, and evaluation metrics party together at scale.

Please reach out to collaborate! 🤝

Pinned Publications
Which LLM Multi-Agent Protocol to Choose?
ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents
Recent Publications
Hongyi Du, Jiaqi Su, Jisen Li, Lijie Ding, Yingxuan Yang, Peixuan Han, Xiangru Tang, Kunlun Zhu, Jiaxuan You (2025). Which LLM Multi-Agent Protocol to Choose?. Under review at ICLR ‘26.
PDF Cite Code Source Document
Cheng Qian, Hongyi Du, Hongru Wang, Xiusi Chen, Yuji Zhang, Avirup Sil, Chengxiang Zhai, Kathleen McKeown, Heng Ji (2025). ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges. arXiv preprint.
PDF Cite Code Source Document
Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, Jiaxuan You (2025). MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents. In ACL ’25.
PDF Cite Code Source Document
Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji (2024). EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents. In ACL ’25.
PDF Cite Code Source Document
Recent News