Shuyue Hu

3
Papers
41
Total Citations

Papers (3)

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

NeurIPS 2025arXiv
36
citations

Scaling Physical Reasoning with the PHYSICS Dataset

NeurIPS 2025
5
citations

Configurable Mirror Descent: Towards a Unification of Decision Making

ICML 2024
0
citations