Miles v0.1 launches: open-source RL framework battle-tested on frontier models
ChengleiSi · x · 2026-09-10
radixark launched Miles v0.1, an open-source RL framework for LLMs and multimodal models focused on correctness, hardware efficiency, and scale. Key points:
- 72 contributors, 1,326 commits, 85 GPU E2E CI tests over 9 months
- Battle-tested on Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, MiniMax H3 and more
- Used in production by Periodic Labs, Modal, Decagon, IBM, Nebius on NVIDIA and AMD hardware
Full technical report covers system design and production practice.
Related event: RadixArk Open-Sources RL Post-Training Framework Miles v0.1(2 posts)→
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26