Paper page - Harness Scaling for Generalizable Agentic Reinforcement Learning

Source: https://huggingface.co/papers/2610.29458

Abstract

Harness Scaling improves agentic reinforcement learning by training across diverse execution configurations, boosting generalization to unseen harnesses.

Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction. Realizing the benefits of these harnesses depends on how effectively the underlying model can make use of them, motivatingreinforcement learningdirectly through the harness. However, existing approaches typically train through a single fixed harness, which can lead to specialization and limited transfer across harness configurations. To address this, we introduceHarness Scaling, a new scaling dimension foragentic RLthat extends training from a single harness to diverse execution configurations. Concretely, we construct a factorized harness space, select a compact training subset with balancedfactorial coverage, and organizecross-harness trainingto combine global coverage with controlled variation for the same task. Across multiple benchmarks, model scales, and RL algorithms,Harness Scalingconsistently improvesgeneralizationto unseen white-box configurations. Moreover, models trained through structured white-box variation transfer effectively to unseen externalblack-box harnesses, outperforming models trained through a single complex black-box harness. These results establish harness diversity as a meaningful scaling dimension foragentic RLand highlight the importance of how this diversity is organized for cross-harnessgeneralization.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2610\.29458

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.29458 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.29458 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.29458 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.