1
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
提出ARMOR方法，用离策锚点样本稳定在策强化学习训练大语言模型，解决训练震荡难题
arXiv:2607.10481v1 Announce Type: cross Abstract: Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language …