StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning

Open Webpage

Yuanqing Yu, Zhefan Wang, Weizhi Ma, Shuai Wang, Chuhan Wu, Zhiqiang Guo, Min Zhang

Published: 2025, Last Modified: 02 Feb 2026CIKM 2025EveryoneRevisionsBibTeXCC BY-SA 4.0