Copyright Notice:

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

M. Besta, N. Blach, A. Kubicek, R. Gerstenberger, M. Podstawski, L. Gianinazzi, J. Gajda, T. Lehmann, H. Niewiadomski, P. Nyczyk, T. Hoefler:

 Graph of Thoughts: Solving Elaborate Problems with Large Language Models

(Proceedings of the AAAI Conference on Artificial Intelligence. Vol 38, Nr. 16, presented in Vancouver, Canada, pages 17682-17690, AAAI Press, Mar. 2024)

Publisher Reference


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.


download article:
access preprint on arxiv:
download slides:


  author={Maciej Besta and Nils Blach and Ales Kubicek and Robert Gerstenberger and MichaƂ Podstawski and Lukas Gianinazzi and Joanna Gajda and Tomasz Lehmann and Hubert Niewiadomski and Piotr Nyczyk and Torsten Hoefler},
  title={{Graph of Thoughts: Solving Elaborate Problems with Large Language Models}},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  location={Vancouver, Canada},
  publisher={AAAI Press},