Structural Embeddings of Tools for Large Language Models

TL;DR

This paper emphasizes the importance of graph-based approaches for integrating external tools with Large Language Models, proposing a framework that hierarchically encodes tool functionalities to improve reasoning and task orchestration.

Contribution

It introduces a novel graph-based framework for orchestrating external tools with LLMs, enabling scalable and structured tool integration for enhanced reasoning.

Findings

Framework demonstrates hierarchical encoding of tool functionalities.

Graph-based approach facilitates scalable tool orchestration.

Potential to improve reasoning with Chain-of-Thought segments.

Abstract

It is evident that the current state of Large Language Models (LLMs) necessitates the incorporation of external tools. The lack of straightforward algebraic and logical reasoning is well documented and prompted researchers to develop frameworks which allow LLMs to operate via external tools. The ontological nature of tool utilization for a specific task can be well formulated with a Directed Acyclic Graph (DAG). The central aim of the paper is to highlight the importance of graph based approaches to LLM-tool interaction in near future. We propose an exemplary framework to guide the orchestration of exponentially increasing numbers of external tools with LLMs,where objectives and functionalities of tools are graph encoded hierarchically. Assuming that textual segments of a Chain-of-Thought (CoT) can be imagined as a tool as defined here, the graph based framework can pave new avenues in that particular direction as well.