Enhancing Tool Retrieval with Iterative Feedback from Large Language Models

TL;DR

This paper introduces an iterative feedback mechanism from large language models to improve tool retrieval accuracy, addressing challenges of complex instructions and tool updates in real-world scenarios.

Contribution

It proposes a novel iterative feedback approach from LLMs to enhance tool retrieval, along with a comprehensive benchmark for evaluation.

Findings

Improved tool retrieval performance in in-domain and out-of-domain settings.

Effective reduction of misalignment between retrieval and usage models.

Demonstrated superiority over existing methods through extensive experiments.

Abstract

Tool learning aims to enhance and expand large language models' (LLMs) capabilities with external tools, which has gained significant attention recently. Current methods have shown that LLMs can effectively handle a certain amount of tools through in-context learning or fine-tuning. However, in real-world scenarios, the number of tools is typically extensive and irregularly updated, emphasizing the necessity for a dedicated tool retrieval component. Tool retrieval is nontrivial due to the following challenges: 1) complex user instructions and tool descriptions; 2) misalignment between tool retrieval and tool usage models. To address the above issues, we propose to enhance tool retrieval with iterative feedback from the large language model. Specifically, we prompt the tool usage model, i.e., the LLM, to provide feedback for the tool retriever model in multi-round, which could progressively improve the tool retriever's understanding of instructions and tools and reduce the gap between the two standalone components. We build a unified and comprehensive benchmark to evaluate tool retrieval models. The extensive experiments indicate that our proposed approach achieves advanced performance in both in-domain evaluation and out-of-domain evaluation.