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.
View on arXiv@article{besta2025_2504.02670,
title={ Affordable AI Assistants with Knowledge Graph of Thoughts },
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 },
journal={arXiv preprint arXiv:2504.02670},
year={ 2025 }
}