Harness Scaling for Generalizable Agentic Reinforcement Learning

One-line takeaway

Renmin University proposes Harness Scaling as a new scaling dimension for agentic RL: training across diverse execution configurations for tool use and context management instead of a single fixed harness, to improve transfer across harness setups.

人民大学提出“执行框架扩展”（Harness Scaling）作为智能体强化学习的新扩展维度：不再只在单一固定框架里训练，而是在多样的工具使用、上下文管理等执行配置上训练，提升在不同框架间的迁移泛化。