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, L. Paleari, J. Hao Andrea Jiang, R. Gerstenberger, Y. Wu, P. Iff, A. Kubicek, P. Nyczyk, D. Khimey, J. Gunnar Hannesson, G. Kwaśniewski, M. Copik, H. Niewiadomski, T. Hoefler:

 Affordable AI Assistants with Knowledge Graph of Thoughts

(arXiv:2504.02670. Apr. 2025)

Abstract

Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face significant challenges, including high operational costs and limited success rates on complex benchmarks like GAIA. To address these issues, we propose the Knowledge Graph of Thoughts (KGoT), an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini, while reducing costs by over 36x compared to GPT-4o. Improvements for recent reasoning models are similar, e.g., 36% and 37.5% for Qwen2.5-32B and Deepseek-R1-70B, respectively. KGoT offers a scalable, affordable, and high-performing solution for AI assistants.

Documents

download article:
access preprint on arxiv:
 

BibTeX

@article{besta2025affordable,
  author={Maciej Besta and Lorenzo Paleari and Jia Hao Andrea Jiang and Robert Gerstenberger and You Wu and Patrick Iff and Ales Kubicek and Piotr Nyczyk and Diana Khimey and Jón Gunnar Hannesson and Grzegorz Kwaśniewski and Marcin Copik and Hubert Niewiadomski and Torsten Hoefler},
  title={{Affordable AI Assistants with Knowledge Graph of Thoughts}},
  journal={arXiv:2504.02670},
  year={2025},
  month={04},
  doi={10.48550/arXiv.2504.02670},
}