Shuyue Hu

5

Papers

41

Total Citations

Papers (5)

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

NeurIPS 2025arXiv

Scaling Physical Reasoning with the PHYSICS Dataset

Configurable Mirror Descent: Towards a Unification of Decision Making

Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach

The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium