Dynamic Tool Dependency Retrieval for Lightweight Function Calling

TL;DR

This paper introduces DTDR, a lightweight, adaptive retrieval method for function calling agents that models tool dependencies dynamically, significantly improving success rates over static retrieval methods.

Contribution

The paper presents DTDR, a novel dynamic retrieval approach that conditions on evolving plans, capturing multi-step dependencies to enhance tool selection in LLM-powered agents.

Findings

DTDR improves function calling success rates by 23% to 104%.

It outperforms static retrieval methods in multiple datasets.

DTDR enhances downstream task accuracy and efficiency.

Abstract

Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving tool calling plan. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that DTDR improves function calling success rates between $23\%$ and $104\%$ compared to state-of-the-art static retrievers.