https://openreview.net/forum?id=PNHjoWcQje&referrer=%5Bthe%20profile%20of%20Jingtao%20Zhan%5D(%2Fprofile%3Fid%3D~Jingtao_Zhan1)
StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs | OpenReview
Despite having powerful reasoning and inference capabilities, Large Language Models (LLMs) still need external tools to acquire real-time information or...
a stepreinforcement learning