Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
Authors:
Preprint
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 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 of 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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Improved Baselines with Visual Instruction Tuning2024
- AgentTuning: Enabling Generalized Agent Abilities for LLMs2024
- TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIsIntelligent Computing, 2024
- Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions2023
- FinQA: A Dataset of Numerical Reasoning over Financial Data2021
- MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms2019