Harness Scaling 如何提升具泛化能力的智能體強化學習
Harness Scaling for Generalizable Agentic Reinforcement Learning
Harness Scaling 透過多種執行配置訓練智能體強化學習模型,提升模型對未見過 harness 的泛化能力。研究以因子化 harness 空間選取訓練子集,並安排跨 harness 訓練;在多個基準測試、模型規模和強化學習算法中,這種方法均改善了對未見白盒配置的泛化。以結構化白盒變化訓練的模型,也能有效遷移至未見的外部黑盒 harness。
Published on Oct 21
Authors:
,
,
,
,
,
,
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, motivating reinforcement learning directly 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 introduce Harness Scaling, a new scaling dimension for agentic RL that extends training from a single harness to diverse execution configurations. Concretely, we construct a factorized harness space, select a compact training subset with balanced factorial coverage, and organize cross-harness training to combine global coverage with controlled variation for the same task. Across multiple benchmarks, model scales, and RL algorithms, Harness Scaling consistently improves generalization to unseen white-box configurations. Moreover, models trained through structured white-box variation transfer effectively to unseen external black-box harnesses, outperforming models trained through a single complex black-box harness. These results establish harness diversity as a meaningful scaling dimension for agentic RL and highlight the importance of how this diversity is organized for cross-harness generalization.
View arXiv page View PDF GitHub Add 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 paper 0
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 paper 0
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 paper 0
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 paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co