Author name: Weiyang Guo, Zesheng Shi, Liye Zhao, Jiayuan Ma, Zeen Zhu, Junxian He, Min Zhang, Jing Li

arXiv:2604.09455v1 Announce Type: new
Abstract: While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face significant limitations: Zero-RL suffers from inefficient e…