Mingyang Sun

Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning

SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance

Beyond Fixed Budgets: Dynamic Reasoning Efficiency Reward for Large Language Model

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making