ToolReAGt: Tool Retrieval for LLM-based Complex Task Solution via Retrieval Augmented Generation

Norbert Braunschweiler, Rama Doddipatla, TUDOR-CATALIN ZORILA

Keywords: Retrieval-Augmented Generation, Tool-augmented AI agents, Information retrieval, Artificial intelligence

TL;DR: Presenting a novel method for improving tool selection accuracy in LLM-based complex task solution scenario via retrieval-augmented generation models in particular using an agentic RAG architecture employing ReAct-prompting.

Abstract: Artificial intelligence agents when deployed to solve complex problems, need to first decompose the task into smaller manageable sub-tasks, and further associate tools if one is required to solve the sub-task. If the size of the set of tools to chose from is large, a retrieval system is usually employed to narrow down the tool choices before the LLM can proceed with associating tools to the sub-tasks. This paper focuses on the retrieval problem to identify the set of relevant tools to solve a complex task given a large pool of tools to chose from using retrieval augmented generation (RAG) and we refer to it as ToolReAGT. The proposed approach employs ReAct prompting to perform the retrieval in an iterative fashion to first identify if a tool is required and then associate one or more tools for each sub-task. This deviates from conventional RAG where an n-best list of tools are identified given the complex task directly. Experiments are presented on the UltraTool benchmark corpus with 1000 complex tasks and over 2000 tools to select from. A conventional RAG-system is established as baseline and compared to the ToolReAGt approach, resulting in an 8.9\% improved retrieval accuracy score recall@5.

Archival Status: Archival (included in proceedings)

Submission Number: 38