Structural Embeddings of Tools for Large Language Models
This addresses the need for better tool integration in LLMs to enhance algebraic and logical reasoning, though it appears incremental as it builds on existing graph-based and Chain-of-Thought approaches.
The paper tackles the problem of orchestrating external tools for Large Language Models (LLMs) by proposing a graph-based framework using Directed Acyclic Graphs (DAGs) to hierarchically encode tool functionalities, aiming to improve reasoning and manage exponentially increasing tools.
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.