1
ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information
无需行为信息就能高效异步训练大模型，ASymPO用不对称规模策略优化让后训练更灵活。
arXiv:2606.03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decouplin…