Large Language Models (LLMs) have demonstrated remarkable progress in utilizing tools, but their closed-source nature and high inference costs pose limitations on their adaptability, necessitating a valid method that leverages smaller, open-sourced models. In this paper, we introduce Toolink, a comprehensive framework that performs task-solving by first creating a toolkit and then integrating the planning and calling of tools through a chain-of-solving (CoS) approach. We first validate the efficacy of Toolink in harnessing the model's creativity and CoS ability on ChatGPT. Subsequently, we curate CoS-GPT, a chain-of-solving dataset designed for tool-using, and finetune the LLaMA-7B model. It results in LLaMA-CoS, a powerful open-source model with advanced tool-planning and tool-calling capabilities. Evaluation on diverse tasks from BIG-bench demonstrates its CoS ability matches that of ChatGPT while its performance surpasses the chain-of-thought approach. Further studies highlight the generalization of LLaMA-CoS to unseen tasks and showcase its capability in using toolkits not explicitly tailored for the target task, affirming its robustness in real-world scenarios. All codes and data are released.

Toolink是一个综合性框架，通过创建工具包，通过chain-of-solving方法实现工具的规划与调用，有效地利用了模型的创造力和chain-of-solving能力，进而提出一个具有先进的工具规划和工具调用能力的开源模型LLaMA-CoS。对多样任务的评估证明LLaMA-CoS的chain-of-solving能力与ChatGPT相媲美，而性能优于chain-of-thought方法，进一步研究突显了LLaMA-CoS对未见过任务的泛化能力，并展示了其在使用针对目标任务的工具包方面的优越性，证实了其在实际场景中的鲁棒性。

Toolink: 通过开源模型的联动求解链将工具包的创建和使用连接起来