News
| [Sep 2026] | Our paper UMAS is accepted to NeurIPS 2026. |
| [Jul 2026] | Our paper SURE is published in npj Artificial Intelligence. |
Research
I’m interested in trustworthy AI, uncertainty quantification, and AI for healthcare.
|
UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems Hanwen Li, Jinhao Duan, Xiaoshuang Shi, Yue Zhang, Tianlong Chen, Kaidi Xu, Chenxi Yuan Advances in Neural Information Processing Systems (NeurIPS), 2026 PDF / Code |
|
SURE: Data-Efficient Safety Guardrailing via Internal Representations and Uncertainty-Weighted Pseudo-Labels Hanwen Li, Jinhao Duan, Chenxi Yuan, James Diffenderfer, Sandeep Madireddy, Bhavya Kailkhura, Kaidi Xu npj Artificial Intelligence, 2026 PDF / Code |
|
From Uncertainty to Action: Learning to Steer LLM Agents Hanwen Li, Jinhao Duan, Guanhua Zhu, Junchi Lu, Bo Shen, Chenxi Yuan, Kaidi Xu arXiv preprint arXiv:2610.09115, 2026 |
Education
- Ph.D. in Informatics, New Jersey Institute of Technology, 2025 – present
- M.S.E. in Electrical Engineering, University of Pennsylvania, 2023 – 2025
- B.E. in Software Engineering, Sichuan University, 2019 – 2023