前沿实验室如何用 MOPD 合并 RL 专家，以及如何用 TRL 实现
原标题：MOPD: how frontier labs merge RL experts into one model and how to do it using TRL
AI 摘要
Hugging Face 博客介绍多教师在线策略蒸馏（MOPD）技术，该技术通过为每个领域训练一个 RL 专家，再将多个专家融合回单一模型，解决单次 RL 训练难以同时提升多领域能力的难题。小米、DeepSeek、Moonshot、NVIDIA、Liquid AI、Mistral 等实验室已采用该技术构建模型。TRL 现已支持 MOPD，AsyncDistillationTrainer 可将每个提示路由到对应的专家教师，同步版 DistillationTrainer 的支持也即将推出。
正文节选
TRL now supports MOPD. AsyncDistillationTrainer routes each prompt to its own expert teacher, and support for the synchronous DistillationTrainer is on its way in #7215. If you already know what MOPD is and are here for the TRL example, jump to MOPD in TRL. One of the post-training techniques that keeps showing up in this year's tech reports is Multi-Teacher On-Policy Distillation (MOPD). Xiaomi named it in January for MiMo-V2-Flash, and since then DeepSeek, Moonshot, NVIDIA, Liquid AI and Mistr