most citedAsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2025★ 1 cited

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Zhenyu Han, Ansheng You, Haibo Wang +16

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated RL frameworks suffer from signif…