【论文】Harness Scaling for Generalizable Agentic Reinforcement Learning

arXiv 2610.29458 · 20 人推荐 · 附代码 RUCAIBox/Harness-Scaling（1 stars）。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.