About me

I am a fifth-year PhD student at IIIS, Tsinghua University, advised by Prof. Andrew C Yao.

My research focuses on developing verifiable, efficient, and evolvable reasoning systems. My specific interests include:

Neural Theorem Proving and Formal Verification via LLM agents
Reinforcement Learning with Verifiable Rewards (RLVR)
Other Topics such as diffusion language models, generalization theory for DL and AI4Physics

Feel free to reach out if you're interested in my research! I am currently seeking positions in related areas and plan to graduate in December 2025.

Publications

Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
Haoxiong Liu, Jiacheng Sun, Zhenguo Li, Andrew C Yao
To appear at ICML 2025

Augmenting Math Word Problems via Iterative Question Composing
Haoxiong Liu*, Yifan Zhang*, Yifan Luo, Andrew C Yao
AAAI-25