Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum


  • Shen Gao Shandong University
  • Zhengliang Shi Shandong University
  • Minghang Zhu Shandong University
  • Bowen Fang Shandong University
  • Xin Xin Shandong University
  • Pengjie Ren Shandong University
  • Zhumin Chen Shandong University
  • Jun Ma Shandong University
  • Zhaochun Ren Leiden University



NLP: (Large) Language Models, NLP: Applications


Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although there are some works that 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 scenario compared to both tuning-free (e.g., ChatGPT, Claude) and tuning-based baselines (e.g., GPT4Tools).




How to Cite

Gao, S., Shi, Z., Zhu, M., Fang, B., Xin, X., Ren, P., Chen, Z., Ma, J., & Ren, Z. (2024). Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 18030-18038.



AAAI Technical Track on Natural Language Processing I