# Miles v0.1 发布：面向生产级后训练的开源 RL 系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-08 08:00
- AIHOT 分数：51
- AIHOT 链接：https://aihot.news/items/cmttkjroo0cb1rofp64mr3dfn
- 原文链接：https://arxiv.org/abs/2609.08368

## AI 摘要

Miles v0.1 是一个全栈、生产就绪的前沿后训练系统，围绕 slime 的设计，将 RL 训练循环各环节按可验证、干净、可定制的原则构建，并已在 https://github.com/radixark/miles 开源。

## 正文

We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each stage of the reinforcement-learning (RL) training loop around a single principle: components should be verified, clean, and customizable. With accuracy, efficiency, reliability, and scalability as first-class goals, Miles aims to make frontier-scale RL accessible to researchers and enterprises alike. This report walks through the system end to end: rollout engines built on SGLang, a trainer with a choice of two backends (NVIDIA Megatron-LM and PyTorch FSDP), and three weight-synchronization transports for different deployment topologies. Beyond full-parameter RL, Miles also supports LoRA RL, on-policy distillation, supervised fine-tuning, and true-on-policy rollout-training alignment, and extends the same architecture to diffusion models. We close with an end-to-end case study: fully asynchronous agentic RL on a GLM-5.2 744B-A40B model over terminal-use coding tasks, running on 64 NVIDIA GB300 GPUs with a median step time of 263 seconds over the first 30 measured steps. Miles is open-sourced at https://github.com/radixark/miles, with the project website at https://miles.radixark.com.