ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency remains a major bottleneck. Existing RL systems commonly rely on asynchronous execution to overlap rollout generation with policy optimization for enhanced efficiency....
Yu Tian, Junwei Su, Hao Xu et al.
· 0 citations