@billxbf: Excited to release Polar, our Agent RL rollout infra for real-world harnesses. Be it Codex, Claude Code, OpenClaw, Herm…
Summary
Polar is an agent RL rollout infrastructure that allows using real-world harnesses as training environments without code changes, supporting models like Codex, Claude Code, OpenClaw, and Hermes.
View Cached Full Text
Cached at: 05/27/26, 03:17 AM
Excited to release 🌟Polar🌟, our Agent RL rollout infra for real-world harnesses. Be it Codex, Claude Code, OpenClaw, Hermes, or your self-made ones 🔥 – Polar takes your harnesses directly as training environments without code change.
Find a problem, design the harness, and https://t.co/cNKMvUqQ54
Similar Articles
@ClementDelangue: We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the …
Hugging Face turned real coding agent harnesses like Claude Code, Codex, Hermes, Pi, and OpenCode into RL training environments via a capture proxy, requiring no changes to the harnesses or training code, with all models, tasks, data, and code fully open sourced.
@ShaokunZhang1: Want to train your own Claude Code/Codex agent with your own model? We are excited to roll out ProRL Agent V2: Polar. A…
NVIDIA releases Polar, an open-source infrastructure for black-box agentic reinforcement learning, enabling training of coding agents like Claude Code or Codex with any agent harness or framework.
@SergioPaniego: frontier agents are this good partly because the model was trained inside the very harness it ships with great to see t…
Sergio Paniego highlights that frontier agents' performance is due to models being trained inside their deployment harness. The new work 'Polar: Agentic RL on Any Harness at Scale' by NVIDIA AI enables turning harnesses like Codex, Claude Code, Qwen Code, or Pi into RL training environments without modifying their internals.
@maximelabonne: Such a cool collab, very happy to see this kind of recipe getting open-sourced Train LFM2.5-2.6B on all the harnesses!
Maximilien Labonne highlights an open-sourced guide to training models with RL inside real agent harnesses like Claude Code, Codex, and OpenCode, enabling training of any model (e.g., LFM2.5-2.6B) on any task set across harnesses.
@akshay_pachaar: HuggingFace just closed a major gap in harness engineering! (the ultimate guide to multi-harness RL) the same open-weig…
Hugging Face researchers present multi-harness reinforcement learning, training LFM2.5-2.6B across Claude Code, Codex, OpenCode and Mini-SWE-Agent using OpenEnv, Harbor and TRL, boosting first-attempt task success from 42.2% to 54.2% with more portable agent behavior.