Mira Murati· @miramurati · X·· 2025-10-28AI 评分51
AI 导读
Mira Murati 分享在线策略蒸馏（on-policy distillation），一种结合强化学习（RL）与监督微调（SFT）优势的训练方法。该方法在数学推理和内部聊天助手上以更低成本超越其他方案，适用于小模型的领域性能提升与持续学习。
正文 · 原文
Combining the benefits of RL and SFT with on-policy distillation, a promising approach for training small models for domain performance and continual learning.
Our latest post explores on-policy distillation, a training approach that unites the error-correcting relevance of RL with the reward density of SFT. When training it for math reasoning and as an internal chat assistant, we find that on-policy distillation can outperform other approaches for a fraction of the cost. https://thinkingmachines.ai/blog/on-policy-distillation/在 X 查看被引用的帖子
来源：Mira Murati · x.com