2025/03/26 by Yifei Lu, Lu, Yifei, Fanghua Ye +15 · 2 citations
Business, Management and Accounting · Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Business Process Modeling and Analysis #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Scientific Computing and Data Management #Service-Oriented Architecture and Web Services #Software Engineering (cs.SE)
paper · pdf · doi:10.48550/arxiv.2503.20840
openalex publication_date 2025/03/26 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28
Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as instruction-enhanced reasoning and supervised fine-tuning, often result in unnecessarily long reasoning paths and face difficulties in verifying the correctness of intermediate steps. In this paper, we propose CodeTool, a novel framework for stepwise code generation that improves LLM tool invocation by leveraging the concise and easily verifiable nature of code. CodeTool incorporates two distinct process rewards: the On-the-spot Reward, which provides immediate feedback on the accuracy of each tool invocation, and the Latent Reward, which assesses the contribution of each step toward overall task completion. By maximizing the cumulative reward of the On-the-spot and Latend Rewards at each step, LLMs are guided to follow efficient and accurate reasoning paths. Extensive experiments on StableToolBench and RestBench-TMDB demonstrate the superiority of CodeTool over existing approaches.