Affordable AI Assistants with Knowledge Graph of Thoughts
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911186405031936 |
|---|---|
| author | Besta, Maciej Paleari, Lorenzo Jiang, Jia Hao Andrea Gerstenberger, Robert Wu, You Hannesson, Jón Gunnar Iff, Patrick Kubicek, Ales Nyczyk, Piotr Khimey, Diana Blach, Nils Zhang, Haiqiang Zhang, Tao Ma, Peiran Kwaśniewski, Grzegorz Copik, Marcin Niewiadomski, Hubert Hoefler, Torsten |
| author_facet | Besta, Maciej Paleari, Lorenzo Jiang, Jia Hao Andrea Gerstenberger, Robert Wu, You Hannesson, Jón Gunnar Iff, Patrick Kubicek, Ales Nyczyk, Piotr Khimey, Diana Blach, Nils Zhang, Haiqiang Zhang, Tao Ma, Peiran Kwaśniewski, Grzegorz Copik, Marcin Niewiadomski, Hubert Hoefler, Torsten |
| contents | 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 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 while also minimizing bias and noise. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini. Moreover, harnessing a smaller model dramatically reduces operational costs by over 36x compared to GPT-4o. Improvements for other models (e.g., Qwen2.5-32B and Deepseek-R1-70B) and benchmarks (e.g., SimpleQA) are similar. KGoT offers a scalable, affordable, versatile, and high-performing solution for AI assistants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02670 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Affordable AI Assistants with Knowledge Graph of Thoughts Besta, Maciej Paleari, Lorenzo Jiang, Jia Hao Andrea Gerstenberger, Robert Wu, You Hannesson, Jón Gunnar Iff, Patrick Kubicek, Ales Nyczyk, Piotr Khimey, Diana Blach, Nils Zhang, Haiqiang Zhang, Tao Ma, Peiran Kwaśniewski, Grzegorz Copik, Marcin Niewiadomski, Hubert Hoefler, Torsten Artificial Intelligence Computation and Language Information Retrieval Machine Learning 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 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 while also minimizing bias and noise. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini. Moreover, harnessing a smaller model dramatically reduces operational costs by over 36x compared to GPT-4o. Improvements for other models (e.g., Qwen2.5-32B and Deepseek-R1-70B) and benchmarks (e.g., SimpleQA) are similar. KGoT offers a scalable, affordable, versatile, and high-performing solution for AI assistants. |
| title | Affordable AI Assistants with Knowledge Graph of Thoughts |
| topic | Artificial Intelligence Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2504.02670 |