CV

Education

B.S. in Electrical Engineering, Department of Electrical Engineering, Tsinghua University, 2016-2020
M.S. in Computer Science, Institute for Interdisciplinary Information Science (IIIS), Tsinghua University, 2020-2023
Ph.D in Electrical Engineering, Texas A&M University, 2024-

June–September 2026: Applied Scientist Intern, Amazon
- Mentor: Yuning Wu
- Conducted research on search-augmented agentic reinforcement learning for mathematical reasoning.
- Developed APIVIS, resulting in Improving Math Reasoning through Value-Guided Informative Search, accepted to the NeurIPS 2026 MATH-AI Workshop.
Spring 2024: Research Assistant (Gap year)
- Tsinghua University
- Duties included: Reinforcement learning research
- Supervisor: Professor Yang Gao
Summer 2022: AI Engineer, JD.com
- Search and recommendation

Improving Math Reasoning through Value-Guided Informative Search
Shaohuai Liu, Yuning Wu, Haoran Liu, Chaoqun Jia, Devin Chen, Kai Wei
NeurIPS MATH-AI Workshop, 2026 · Accepted
Iterative Gumbel Planning for Continuous Control
Shaohuai Liu, Weirui Ye, Yilun Du†, Le Xie†
† Co-corresponding authors.
NeurIPS, 2026 · Accepted
Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
Shaohuai Liu, Weirui Ye, Yilun Du, Le Xie
arXiv, 2026
Real-time power scheduling through reinforcement learning from demonstrations
Shaohuai Liu, Jinbo Liu, Nan Yang, Yupeng Huang, Qirong Jiang, Yang Gao
Electric Power Systems Research, 2024
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
Shengjie Wang, Shaohuai Liu, Weirui Ye, Jiacheng You, Yang Gao
ICML, 2024 · Spotlight
SpeedyZero: Mastering Atari Games with Limited Data and Time
Yixuan Mei, Jiaxuan Gao, Weirui Ye, Shaohuai Liu, Yang Gao, Yi Wu
ICLR, 2023
Mastering Atari Games with Limited Data
Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, Yang Gao
NeurIPS, 2021