Affordable AI Assistants with Knowledge Graph of Thoughts

• URL: http://arxiv.org/abs/2504.02670v2
• Date: Thu, 10 Apr 2025 14:44:34 GMT
• Title: Affordable AI Assistants with Knowledge Graph of Thoughts
• Authors: Maciej Besta, Lorenzo Paleari, Jia Hao Andrea Jiang, Robert Gerstenberger, You Wu, Patrick Iff, Ales Kubicek, Piotr Nyczyk, Diana Khimey, Jón Gunnar Hannesson, Grzegorz Kwaśniewski, Marcin Copik, Hubert Niewiadomski, Torsten Hoefler,
• Abstract summary: Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains.<n>We propose Knowledge Graph of Thoughts (KGoT), an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs)<n>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.
• Score: 15.045446816762675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A Showdown of ChatGPT vs DeepSeek in Solving Programming Tasks [2.66269503676104]
  This study evaluates two leading models: ChatGPT 03-mini and DeepSeek-R1 on their ability to solve competitive programming tasks from Codeforces.<n>Our results indicate that while both models perform similarly on easy tasks, ChatGPT outperforms DeepSeek-R1 on medium-difficulty tasks.
  arXiv  Detail & Related papers  (2025-03-16T14:35:36Z)
• Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning [55.6623318085391]
  Recent large language model (LLM) reasoning suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth.<n>This paper presents the first investigation into integrating step-wise knowledge graph retrieval with step-wise reasoning.<n>We propose KG-RAR, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model.
  arXiv  Detail & Related papers  (2025-03-03T15:20:41Z)
• Intelligent Mobile AI-Generated Content Services via Interactive Prompt Engineering and Dynamic Service Provisioning [55.641299901038316]
  AI-generated content can organize collaborative Mobile AIGC Service Providers (MASPs) at network edges to provide ubiquitous and customized content for resource-constrained users.<n>Such a paradigm faces two significant challenges: 1) raw prompts often lead to poor generation quality due to users' lack of experience with specific AIGC models, and 2) static service provisioning fails to efficiently utilize computational and communication resources.<n>We develop an interactive prompt engineering mechanism that leverages a Large Language Model (LLM) to generate customized prompt corpora and employs Inverse Reinforcement Learning (IRL) for policy imitation.
  arXiv  Detail & Related papers  (2025-02-17T03:05:20Z)
• MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning [17.437573206368494]
  Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. Current algorithms suffer from low sample efficiency, limiting their practical applicability. We present MENTOR, a method that improves both the architecture and optimization of RL agents.
  arXiv  Detail & Related papers  (2024-10-19T04:31:54Z)
• Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning [19.442426875488675]
  We propose Paths-over-Graph (PoG), a novel method that enhances Large Language Models (LLMs) reasoning by integrating knowledge reasoning paths from KGs.<n>PoG tackles multi-hop and multi-entity questions through a three-phase dynamic multi-hop path exploration.<n>In experiments, PoG with GPT-3.5-Turbo surpasses ToG with GPT-4 by up to 23.9%.
  arXiv  Detail & Related papers  (2024-10-18T06:57:19Z)
• ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning [78.42927884000673]
  ExACT is an approach to combine test-time search and self-learning to build o1-like models for agentic applications.<n>We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore decision space on the fly.<n>Next, we introduce Exploratory Learning, a novel learning strategy to teach agents to search at inference time without relying on any external search algorithms.
  arXiv  Detail & Related papers  (2024-10-02T21:42:35Z)
• SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories [55.161075901665946]
  Super aims to capture the realistic challenges faced by researchers working with Machine Learning (ML) and Natural Language Processing (NLP) research repositories. Our benchmark comprises three distinct problem sets: 45 end-to-end problems with annotated expert solutions, 152 sub problems derived from the expert set that focus on specific challenges, and 602 automatically generated problems for larger-scale development. We show that state-of-the-art approaches struggle to solve these problems with the best model (GPT-4o) solving only 16.3% of the end-to-end set, and 46.1% of the scenarios.
  arXiv  Detail & Related papers  (2024-09-11T17:37:48Z)
• DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs [70.54226917774933]
  We propose the DecompositionAlignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism. We show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA.
  arXiv  Detail & Related papers  (2024-06-11T09:09:37Z)
• Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning [56.82041895921434]
  Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities. When used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2024-03-29T03:48:12Z)
• KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning [3.103778949672541]
  We propose a framework that integrates CoT reasoning, Knowledge Graphs, and multiple modalities for a comprehensive understanding of multimodal tasks. KAM-CoT adopts a two-stage training process with KG grounding to generate effective rationales and answers. We achieve an average accuracy of 93.87%, surpassing GPT-3.5 (75.17%) by 18% and GPT-4 (83.99%) by 10%.
  arXiv  Detail & Related papers  (2024-01-23T15:56:11Z)
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts [170.01089233942594]
  MathVista is a benchmark designed to combine challenges from diverse mathematical and visual tasks. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning.
  arXiv  Detail & Related papers  (2023-10-03T17:57:24Z)
• LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities [66.36633042421387]
  Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning evaluated. We propose AutoKG, a multi-agent-based approach employing LLMs and external sources for KG construction and reasoning.
  arXiv  Detail & Related papers  (2023-05-22T15:56:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.