Zhicheng Yang

PhD Candidate in Large Language Model Reasoning

I'm pursuing a PhD degree. I work on reasoning-centric large language models, with current interests in solve-and-verify paradigms, reasoning data synthesis, and test-time scaling. My recent work focuses on advanced expert-level mathematical reasoning, verification, efficiency & readability CoT, and agentic reasoning.

View Selected Papers Get in Touch
Google Scholar GitHub Email
Portrait of Zhicheng Yang

Research Interests

Solve & Verify CoT Synthesis Test-Time Scaling

Background

Experience

  • LLM Research Intern, ByteDance Seed
  • LLM Research Intern, Huawei Noah's Ark Lab
  • Recommender System Intern, ByteDance Douyin

Education

  • 2020 - 2023: Master in Pattern Recognition and Intelligent Systems, Sun Yat-sen University
  • 2016 - 2020: B.Sc. in Computer Science and Technology, Sun Yat-sen University

Honors & Awards

  • National First Prize, Contemporary Undergraduate Mathematical Contest in Modeling
  • First Prize Scholarship, Sun Yat-sen University

Professional Service

  • Area Chair, ACL Rolling Review (ARR), January 2026
  • Reviewer for ICML, NeurIPS, ICLR, ACL, EMNLP, NAACL, and TNNLS

News

Sep 2025

Two papers were accepted to EMNLP 2025.

Jan 2025

Co-organizing the 2nd AI4MATH Workshop at ICML 2025.

Jan 2025

One paper was accepted to ICLR 2025.

May 2024

Served as challenge lead organizer for Automated Optimization Problem-Solving with Code at ICML 2024.

Preprints

Current directions in efficient and verifiable LLM reasoning.

Preprint

🔥 Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Wenlei Shi, Yiwei Wang, Xiaodan Liang, Jing Tang

Paper Code

Preprint

🔥🔥 Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie, Yiwei Wang, Xiaodan Liang, Jing Tang

Paper Code

Preprint

TreeRPO: Tree Relative Policy Optimization

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang

Paper Code

Preprint

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang

Paper Code

Selected Papers

Representative publications in reasoning, mathematical intelligence, and verification.

ICLR 2025

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, Jing Tang

The Thirteenth International Conference on Learning Representations

Paper Code

CVPR 2026

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Yongxin Wang, Zhicheng Yang, Meng Cao, Mingfei Han, Haokun Lin, Yingying Zhu, Xiaojun Chang, Xiaodan Liang

IEEE Conference on Computer Vision and Pattern Recognition

Paper

NeurIPS 2024

Proving Theorems Recursively

Haiming Wang, Huajian Xin, Zhengying Liu, Wenda Li, Yinya Huang, Jianqiao Lu, Zhicheng Yang, Jing Tang, Jian Yin, Zhenguo Li, Xiaodan Liang

Advances in Neural Information Processing Systems 37

Paper

Findings of EMNLP 2024

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

Conference on Empirical Methods in Natural Language Processing

Paper Code

ACL 2024

CLOMO: Counterfactual Logical Modification with Large Language Models

Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics

Paper

Findings of NAACL 2024

ATG: Benchmarking Automated Theorem Generation for Generative Language Models

Xiaohan Lin, Qingxing Cao, Yinya Huang, Zhicheng Yang, Zhengying Liu, Zhenguo Li, Xiaodan Liang

Findings of the Association for Computational Linguistics: NAACL 2024

Paper

Findings of EMNLP 2022

LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-Enhanced Learning

Zhicheng Yang*, Jinghui Qin*, Jiaqi Chen, Liang Lin, Xiaodan Liang

Conference on Empirical Methods in Natural Language Processing

Paper Code

Findings of NAACL 2022

Unbiased Math Word Problems Benchmark for Mitigating Solving Bias

Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang

Annual Conference of the North American Chapter of the ACL

Paper Code

TNNLS 2023

Template-based Contrastive Distillation Pre-training for Math Word Problem Solving

Jinghui Qin*, Zhicheng Yang*, Jiaqi Chen, Xiaodan Liang, Liang Lin

IEEE Transactions on Neural Networks and Learning Systems

Paper