Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
Preprint
Abstract
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although some works employ open-source LLMs for the tool learning task, most of them are trained in a controlled environment in which LLMs only learn to execute the human-provided tools. However, selecting proper tools from the large toolset is also a crucial ability for the tool learning model to be applied in real-world applications. Existing methods usually directly employ self-instruction methods to train the model, which ignores differences in tool complexity. In this paper, we propose the Confucius, a novel tool learning framework to train LLM to use complicated tools in real-world scenarios, which contains two main phases: (1) We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum; (2) thenceforth, we propose the Iterative Self-instruct from Introspective Feedback (ISIF) to dynamically construct the dataset to improve the ability to use the complicated tool. Extensive experiments conducted on both controlled and real-world settings demonstrate the superiority of our tool learning framework in the real-world application scenarios compared to both tuning-free (e.g. ChatGPT, Claude) and tuning-based baselines (e.g. GPT4Tools).Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- GeneGPT: augmenting large language models with domain tools for improved access to biomedical informationBioinformatics, 2024
- Gorilla: Large Language Model Connected with Massive APIs2024
- Generative Agents: Interactive Simulacra of Human Behavior2023
- WebCPM: Interactive Web Search for Chinese Long-form Question Answering2023
- Product-Aware Answer Generation in E-Commerce Question-Answering2019