Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models

TL;DR

This paper introduces Tool Graph Retriever (TGR), a novel method that leverages tool dependencies via graph convolution to improve tool retrieval for large language models, outperforming existing approaches.

Contribution

The paper proposes a dependency-aware tool retrieval method using graph convolution, addressing the limitation of independent tool consideration in prior methods.

Findings

TGR achieves state-of-the-art performance on multiple datasets.

Tool dependencies significantly enhance retrieval accuracy.

Graph-based representations improve tool integration efficiency.

Abstract

With the remarkable advancement of AI agents, the number of their equipped tools is increasing rapidly. However, integrating all tool information into the limited model context becomes impractical, highlighting the need for efficient tool retrieval methods. In this regard, dominant methods primarily rely on semantic similarities between tool descriptions and user queries to retrieve relevant tools. However, they often consider each tool independently, overlooking dependencies between tools, which may lead to the omission of prerequisite tools for successful task execution. To deal with this defect, in this paper, we propose Tool Graph Retriever (TGR), which exploits the dependencies among tools to learn better tool representations for retrieval. First, we construct a dataset termed TDI300K to train a discriminator for identifying tool dependencies. Then, we represent all candidate tools as a tool dependency graph and use graph convolution to integrate the dependencies into their representations. Finally, these updated tool representations are employed for online retrieval. Experimental results on several commonly used datasets show that our TGR can bring a performance improvement to existing dominant methods, achieving SOTA performance. Moreover, in-depth analyses also verify the importance of tool dependencies and the effectiveness of our TGR.