Xuan Li

About Me

I am Xuan Li, a second-year Ph.D. student at TMLR Group of Hong Kong Baptist University, fortunate to be advised by Prof. Bo Han and co-advised by Prof. Lu (Eric) Zhang, and working with Prof. Jiangchao Yao. My research focuses on trustworthy machine reasoning for scientific discovery, aiming to turn advanced reasoning capabilities into reliable, verifiable scientific tools.

My research interests include:

• Agentic Systems for Complex Reasoning: Methodologies for continuously improving reasoning quality : [AlphaApollo]
• Probing Reasoning Reliability: Investigating robustness and safety in LLMs: [DeepInception]
• Advancing Reasoning for Scientific Discovery: Reasoning for molecular property prediction and optimization: [Neural Atoms], [RePO]

Selected Research Work

* Equal contribution, ✉️ Corresponding author. Full list on Google Scholar.

AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning

Zhanke Zhou, Chentao Cao, Xiao Feng, Xuan Li, Zongze Li, Xiangyu Lu, Jiangchao Yao, Weikai Huang, Linrui Xu, Tian Cheng, Guanyu Jiang, Yiming Zheng, Brando Miranda, Tongliang Liu, Sanmi Koyejo, Masashi Sugiyama, Bo Han✉️

Tenical Report. [Paper] [Code] [Website]

Reference-Guided Policy Optimization for Molecular Optimization via LLM Reasoning

Xuan Li, Zhanke Zhou, Zongze Li, Jiangchao Yao, Yu Rong, Lu Zhang, Bo Han✉️

ICLR 2026. [Paper] [Code]

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Zhanke Zhou*, Zhaocheng Zhu*, Xuan Li*, Mikhail Galkin, Xiao Feng, Sanmi Koyejo, Jian Tang, Bo Han✉️

ICLR 2026. [Paper] [Code] [Website]

DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Xuan Li*, Zhanke Zhou*, Jianing Zhu*, Jiangchao Yao, Tongliang Liu, Bo Han✉️

NeurIPS 2024 SafeGenAI Workshop. [Paper] [Code] [CN Video] [CN Blog] [DeepTech]

Neural atoms: Propagating Long-range Interaction in Molecular Graphs Through Efficient Communication Channel

Xuan Li*, Zhanke Zhou*, Jiangchao Yao, Yu Rong, Lu Zhang, Bo Han✉️

ICLR 2024. [Paper] [Code] [EN Video] [CN Video]

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

Zhanke Zhou, Chenyu Zhou, Xuan Li, Jiangchao Yao✉️, Quanming Yao, Bo Han✉️

ICML 2023. [Paper] [Code] [EN Video] [CN Video] [CN Blog]