Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model

arXiv:2310.05155v2 Announce Type: replace
Abstract: 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 …

abstract adaptability arxiv costs cs.ai cs.cl framework inference inference costs language language models large language large language models limitations llms nature paper progress through toolkit tools type