Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem SolvingAgentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving

NeurIPS 20252025

Xinji Mai^*, Haotian Xu^*, Xing W, Weinong Wang, Yingying Zhang, Wenqiang Zhang

Figure from the 图片来源：original paper原论文 ↗

Studies how reinforcement learning teaches models to use code for mathematical reasoning, and how this ability scales.

研究强化学习如何让模型自主调用代码进行数学推理，以及这种能力的规模化规律。