Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, Torsten Hoefler

We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.

• Anthropic
• Alignment Research Center
• Anthropic
• Truthful AI
• University of California, Berkeley
• Warsaw University of Technology
• IDEAS Research Institute
• University of Warsaw
• VIZJA University
• Warsaw University of Technology
• Universidad Complutense de Madrid
• Warsaw University of Technology
• Jagiellonian University
• Sano Centre for Computational Medicine
• University of Verona
• Warsaw University of Technology
• Harvard University
• Warsaw University of Technology
• Snowflake
• Adam Mickiewicz University
• Jagiellonian University
• Warsaw University of Technology