Andrew Zhao

PhD student, Automation, Tsinghua University, Tsinghua University

Joined

April 2022

Names

Andrew Zhao (Preferred)

Emails

****@mails.tsinghua.edu.cn (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Automation, Tsinghua University, Tsinghua University (mails.tsinghua.edu.cn)

2021 – 2027

Researcher

Microsoft (microsoft.com)

2024 – 2024

Researcher

BIGAI (bigai.ai)

2024 – 2024

Intern

Peking University (pku.edu.cn)

2020 – 2021

MS student

University of Southern California (usc.edu)

2019 – 2020

Undergrad student

University of British Columbia (ubc.ca)

2012 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Gao Huang

2021 – 2027

Expertise

Language Agents

2023 – 2027

Reinforcement Learning

2021 – 2027

Publications

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
Yiran Wu, Mauricio Velazco, Andrew Zhao, Manuel Raúl Meléndez Luján, Srisuma Movva, Yogesh K Roy, Quang Nguyen, Roberto Rodriguez, Qingyun Wu, Michael Albada, Julia Kiseleva, Anand Mudgerikar
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xiong-Hui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin
- NeurIPS 2025 poster
- Readers: Everyone
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang
- NeurIPS 2025 oral
- Readers: Everyone
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang
- NeurIPS 2025 spotlight
- Readers: Everyone
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang
- AI4Math@ICML25 Oral
- Readers: Everyone
DiveR-CT: Diversity-enhanced Red Teaming with Relaxing Constraints
Andrew Zhao, Quentin Xu, Matthieu Lin, Shenzhi Wang, Yong-jin Liu, Zilong Zheng, Gao Huang
- NextGenAISafety 2024 Poster
- Readers: Everyone
Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation
Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Provable General Function Class Representation Learning in Multitask Bandits and MDP
Rui Lu, Andrew Zhao, Simon Shaolei Du, Gao Huang
- Published: 31 Oct 2022, Last Modified: 12 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
A Mixture Of Surprises for Unsupervised Reinforcement Learning
Andrew Zhao, Matthieu Gaetan Lin, Yangguang Li, Yong-jin Liu, Gao Huang
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Provable General Function Class Representation Learning in Multitask Bandits and MDP
Rui Lu, Andrew Zhao, Simon S. Du, Gao Huang
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- NeurIPS 2022
- Readers: Everyone

View all 12 publications

Co-Authors

View all 50 co-authors