About
I am a second-year CS PhD student at the School of Computing and Augmented Intelligence, Arizona State University, advised by Prof. Hua Wei in the DaRL Lab. Previously, I was a research assistant at the Institute of AI Industry Research, Tsinghua University, working with Pengfei Li, advised by Prof. Peng Li and Prof. Yilun Chen. I also worked as an RA under the supervision of Prof. Xiao Luo (now at UW-Madison). I obtained my Bachelor's degree in Computer Science from Xi'an Jiaotong University, advised by Prof. Yuanqi Su.
My long-term vision is to develop agents that learn continuously through real-world interactions, unraveling the complexity of intelligence in both artificial neural networks and the human brain.
Selected Publications
View All →LangMARL: Natural Language Multi-Agent Reinforcement Learning
Huaiyuan Yao, Longchao Da, Xiaoou Liu, Charles Fleming, Tianlong Chen, Hua Wei†
Accepted at EMNLP 2026
Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties
Huaiyuan Yao, Wanpeng Xu, Justin Turnau, Nadia Kellam, Hua Wei†
Conference of the European Chapter of the Association for Computational Linguistics (EACL)
Accepted at EACL 2026
CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic
Huaiyuan Yao, Longchao Da, Vishnu Nandam, Justin Turnau, Zhiwei Liu, Linsey Pang, Hua Wei†
CIKM 2024 Workshop, SDM 2025
Accepted at SDM 2025
News
Three papers get accepted by EMNLP 2026!
Our paper AURORA: Attention-intended Dual Verification with Adaptive Rollback for Large Language Model Agents has been accepted by IROS 2026!
Glad to receive University Graduate Fellowship (UGF) for Summer 2026!
Thrilled to receive a Research Intern offer from Honda Research Institute! See you in Mountain View, CA! 🚗
Honored to be accepted to AI-SCORE 2026 at UIUC, exploring the synergy between Operations Research (OR) and Computer Science (CS) communities. See you in Chicago! 🌆
Our work Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition has been accepted by ACL 2026 Main Conference! 🎉
New preprint released: LangMARL: Natural Language Multi-Agent Reinforcement Learning.
Glad to receive University Graduate Fellowship (UGF) for Spring 2026!
Our work How Effective is In-Context Learning with Large Language Models for Rare Cell Identification in Single-Cell Expression Data? has been accepted by ICDM 2026!
New paper released: RULERS: Locked Rubrics and Evidence-Anchored Scoring for Robust LLM Evaluation.