Radixark releases Miles v0.1, a full-stack RL training system
Released Miles v0.1, a full-stack RL training system for frontier-class post-training. It provides an SGLang-based rollout engine, two trainer backends (Megatron-LM and PyTorch FSDP) and 3 weight-sync transfer paths for different deployment topologies, and extends the same architecture beyond full-parameter RL to LoRA RL, on-policy distillation, SFT, true-on-policy rollout-training alignment and even diffusion models. The authors claim that training GLM-5.2 744B-A40B on 64 NVIDIA GB300s with fully asynchronous agentic RL on terminal coding tasks recorded a median step time of 263 seconds over the first 30 steps.
Why it matters
With agentic RL infrastructure for models with hundreds of billions of parameters coming out as open source, the barrier to entry for frontier post-training has come down to reach beyond a handful of large labs.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.08368Added in Week 38, 2026 · See that week