KVCache.AI(@KVCache_AI):Congrats to the Miles team on the v0.1 launch! 🚀 AgentENV is now integrated with Miles v0.1 as a sandbox backend for agentic RL. Built for high-performance, production-scale post-training, Miles provides a powerful foundation for agentic RL with fully asynchronous training and fast, flexible rollouts. AgentENV complements Miles by providing isolated, fast-starting Firecracker microVMs for every rollout, giving agents fresh environments to write code, execute commands, and call tools without sandbox startup becoming the bottleneck. Validated on a sustained GRPO run across the full Terminal-Bench-2 suite, this integration powered ~3,400 episodes across 55 rollouts with GLM-4.7-Flash on 8×H200s. Every episode ran in a fresh, snapshot-warmed microVM, while a single m7i.metal-24xl AgentENV server sustained 64 concurrent environments throughout.

2026.08.18 16:13

Congrats to the Miles team on the v0.1 launch! 🚀 AgentENV is now integrated with Miles v0.1 as a sandbox backend for agentic RL. Built for high-performance, production-scale post-training, Miles provides a powerful foundation for agentic RL with fully asynchronous training and fast, flexible rollouts. AgentENV complements Miles by providing isolated, fast-starting Firecracker microVMs for every rollout, giving agents fresh environments to write code, execute commands, and call tools without sandbox startup becoming the bottleneck. Validated on a sustained GRPO run across the full Terminal-Bench-2 suite, this integration powered ~3,400 episodes across 55 rollouts with GLM-4.7-Flash on 8×H200s. Every episode ran in a fresh, snapshot-warmed microVM, while a single m7i.metal-24xl AgentENV server sustained 64 concurrent environments throughout.

RadixArk@radixark

2026.08.18 16:09

Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models. RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale. Over the past 9 months, 72 contributors have landed 1,326 commits, 85 GPU E2E CI tests, battle-testing Miles on frontier open models like Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, Inkling, MiniMax H3, etc. Miles powers frontier-model development and production RL workloads at @humansand, @periodiclabs, @modal, @DecagonAI, @Eigent_AI, @nebiusai, @IBM and more, on both @NVIDIAAI and @AIatAMD hardware. Here is what we built, and why teams picked Miles🧵

Forward to community