Publications

2026

Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
Xuan Yang, Hao Xu, Tingfeng Hui, Hongsheng Xin, Kaike Zhang, Chunxiao Liu, Ning Miao
arXiv  ·  02 Jun 2026  ·  arXiv:2606.03318
Code
Dataset
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
Tingfeng Hui, Hao Xu, Pengyu Zhu, Hongsheng Xin, Kun Zhan, Sen Su, Chunxiao Liu, Ning Miao
arXiv  ·  18 May 2026  ·  arXiv:2605.18548
Code
Dataset
Verifier-Backed Hard Problem Generation for Mathematical Reasoning
Verifier-Backed Hard Problem Generation for Mathematical Reasoning
Yuhang Lai*, Jiazhan Feng*, Yee Whye Teh, Ning Miao
arXiv  ·  07 May 2026  ·  arXiv:2605.06660
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Xuan Yang*, Jiayu Liu*, Yuhang Lai*, Hao Xu, Zhenya Huang, Ning Miao
arXiv  ·  03 Mar 2026  ·  arxiv:2603.03031
Code
Dataset
Linear Dynamics in the RLVR Training of Large Language Models
Linear Dynamics in the RLVR Training of Large Language Models
Tianle Wang*, Jiayu Liu*, Zhongyuan Wu*, Shenghao Jin, Wei Chen, Hao Xu, Ning Miao
arXiv  ·  25 Jan 2026  ·  arxiv:2601.04537
Code
Dataset

2025

Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
Qiyuan Liu*, Hao Xu*, Xuhong Chen, Wei Chen, Yee Whye Teh, Ning Miao
arXiv  ·  03 Oct 2025  ·  arxiv:2510.01925
Deep Thinking by Markov Chain of Continuous Thoughts
Deep Thinking by Markov Chain of Continuous Thoughts
Jiayu Liu, Zhenya Huang, Xuan Yang, Tianyun Ji, Anya Sims, Hao Xu, Enhong Chen, Yee Whye Teh, Ning Miao
arXiv  ·  29 Sep 2025  ·  arXiv:2509.25020
Code