Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems

Ye Li
1/10/2024
cs.AI

No official code found. Best implementation: microsoft/GoTFlow (81 stars, MIT, last commit 2024-04-18).

Abstract

This paper presents Graph-of-Thought (GoT), a new model for workflow automation that enhances the flexibility and efficiency of Large Language Models (LLMs) in complex task execution. GoT advances beyond traditional linear and tree-like cognitive models with a graph structure that enables dynamic path selection. The open-source engine GoTFlow demonstrates the practical application of GoT, facilitating automated, data-driven decision-making across various domains. Despite challenges in complexity and transparency, GoTFlow's potential for improving business processes is significant, promising advancements in both efficiency and decision quality with continuous development.

View on arXivView PDF

Code Implementations(1)

microsoft/GoTFlowCommunity100%
MIT

a workflow engine for Graph-of-Thought

819Python, BatchfileOct 31, 20232 years agoMIT

Similar Papers

Generating Structured Plan Representation of Procedures with LLMs

84% match2025

ChainBuddy: An AI Agent System for Generating LLM Pipelines

79% match2024

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

78% match2025

Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

78% match2026

Creating Scalable AGI: the Open General Intelligence Framework

78% match1 repo2024

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

77% match1 repo1.0k2025

Cite this paper

@article{li2024graphofthought,
  title  = {Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems},
  author = {Ye Li},
  year   = {2024},
  eprint = {2401.06801},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.06801v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.06801.svg)](https://codeofpaper.com/paper/2401.06801)

Discussion