# Polar: Agentic RL on Any Harness at Scale

arXiv: https://arxiv.org/abs/2605.24220 · HTML: https://mlsanity.com/paper/2605.24220/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2026.

## Built on by (most cited first, 14 of 14)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [OpenForgeRL: Train Harness-native Agents in Any Environment](https://mlsanity.com/paper/2607.21557/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Intern-S2-Preview: Scientific Agentic Foundation Model](https://mlsanity.com/paper/2608.13505/) (2026)
- [LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents](https://mlsanity.com/paper/2608.17393/) (2026)
- [FrogNano: Training a 4B Coding Agent via Online Task Synthesis](https://mlsanity.com/paper/2609.07925/) (2026)
- [ClawGym II: Exploring Black-Box RL on Agent Harness](https://mlsanity.com/paper/2608.16798/) (2026)
- [Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence](https://mlsanity.com/paper/2609.04518/) (2026)
- [HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.13739/) (2026)
- [Finding the Right Fit: Model-Harness Interactions across Agent Tasks](https://mlsanity.com/paper/2610.00917/) (2026)
- [Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.21653/) (2026)
- [SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation](https://mlsanity.com/paper/2609.32391/) (2026)
- [QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents](https://mlsanity.com/paper/2609.33848/) (2026)
- [LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches](https://mlsanity.com/paper/2610.06647/) (2026)

## Abstract (arXiv)

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains difficult and often loses important training signals. We bridge this gap with polar, a rollout framework for scalable asynchronous RL over arbitrary agent harnesses. Polar treats the agent harness as a black box: it proxies LLM API calls, records token-level model interactions, and reconstructs token-faithful trajectories for training. Each rollout node efficiently manages runtime prewarming, agent execution, trajectory reconstruction, and evaluation in parallel, exposing asynchronous service endpoints that can be consumed by independent trainers at scale. This decoupled design makes Polar agnostic to agent harnesses, training infrastructure, and RL algorithms while improving compute utilization for long-running agent workloads. We validate polar by training agents on software-engineering tasks with popular coding harnesses. Using simple GRPO, polar improves Qwen3.5-4B by 22.6, 4.8, 0.6 and 6.2 points on SWE-Bench Verified with the Codex, Claude Code, Qwen Code and Pi harnesses, respectively. We further demonstrate Polar for offline data generation over custom harnesses and ablate trajectory reconstruction strategies. Polar rewrites its preceding work, Prorl Agent, and has been registered as one of NeMo Gym environments.