# Affordable AI Assistants with Knowledge Graph of Thoughts

arXiv: https://arxiv.org/abs/2504.02670 · HTML: https://mlsanity.com/paper/2504.02670/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 107 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 28 of 28)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph](https://mlsanity.com/paper/2403.00839/) (2024)
- [Reasoning Language Models: A Blueprint](https://mlsanity.com/paper/2501.11223/) (2025)
- [RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing](https://mlsanity.com/paper/2404.19543/) (2024)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [TapeAgents: a Holistic Framework for Agent Development and Optimization](https://mlsanity.com/paper/2412.08445/) (2024)
- [Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical Education](https://mlsanity.com/paper/2308.00479/) (2023)
- [CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks](https://mlsanity.com/paper/2406.02524/) (2024)
- [Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies](https://mlsanity.com/paper/2402.03628/) (2024)
- [Generator-Retriever-Generator Approach for Open-Domain Question Answering](https://mlsanity.com/paper/2307.11278/) (2023)
- [ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling](https://mlsanity.com/paper/2402.13547/) (2024)
- [Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models](https://mlsanity.com/paper/2305.10276/) (2023)
- [Updating Embeddings for Dynamic Knowledge Graphs](https://mlsanity.com/paper/2109.10896/) (2021)
- [Demystifying Higher-Order Graph Neural Networks](https://mlsanity.com/paper/2406.12841/) (2024)
- [Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning](https://mlsanity.com/paper/2402.01602/) (2024)
- [Hardware Acceleration for Knowledge Graph Processing: Challenges & Recent Developments](https://mlsanity.com/paper/2408.12173/) (2024)

## Built on by (most cited first, 6 of 6)

- [Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation](https://mlsanity.com/paper/2601.17915/) (2026)
- [Psychologically Enhanced AI Agents](https://mlsanity.com/paper/2509.04343/) (2025)
- [AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models](https://mlsanity.com/paper/2601.00561/) (2026)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs](https://mlsanity.com/paper/2605.22195/) (2026)
- [Performance Foundations of Parallel & Distributed Reasoning Language Models](https://mlsanity.com/paper/2608.27046/) (2026)

## Abstract (arXiv)

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.