Authors : Asma Hamad Alharbi; Hafiz Farooq Ahmad

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/bdhz9tcf

Scribd : https://tinyurl.com/29e98aw3

DOI : https://doi.org/10.38124/ijisrt/26apr2488

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The integration of large language models (LLMs) with knowledge graphs (KGs) has emerged as a promising approach to enhance reasoning, explainability, and decision-making in intelligent systems. However, LLMs inherently lack structured knowledge representation, leading to limitations such as hallucinations and reduced reliability, particularly in industrial applications. This study presents a systematic review of autonomous knowledge graphs for LLM-based agents, focusing on their role in enabling knowledge-driven and agentic AI systems in industry. Guided by PRISMA methodology, a comprehensive search across major scientific databases resulted in 33 relevant studies, which were classified into four research dimensions: architectures, KG construction and evolution, KG-based reasoning, and industrial applications. The findings reveal that multi-agent architectures and GraphRAG-based approaches dominate current research, while LLMs enable automated and dynamic knowledge graph lifecycle management. Furthermore, applications in manufacturing, digital twins, and industrial IoT demonstrate significant improvements in efficiency and decision-making. Despite these advancements, challenges related to scalability, computational cost, domain dependency, and lack of real-world validation persist. This review concludes that autonomous knowledge graphs play a critical role in advancing LLM-based agents toward reliable and scalable industrial deployment, while highlighting key research gaps and future directions for developing robust, explainable, and industry-ready AI systems.

Keywords : Autonomous Knowledge Graphs ; LLM-based Agents ; Multi-Agent Systems; Graph Retrieval-Augmented Generation (GraphRAG) ; Industrial Artificial Intelligence; Smart Manufacturing.

References :

1. N. Aamer, M. N. Asim, S. Munir, and A. Dengel, “Automating AI discovery for biomedicine through knowledge graphs and LLM agents,” bioRxiv, 2025.
2. P. Anokhin et al., “AriGraph: Learning knowledge graph world models with episodic memory for LLM agents,” arXiv preprint arXiv:2407.04363, 2024.
3. J. Bai et al., “AutoSchemaKG: Autonomous knowledge graph construction through dynamic schema induction from web-scale corpora,” arXiv preprint, 2025.
4. H. Bian, “LLM-empowered knowledge graph construction: A survey,” arXiv preprint, 2025.
5. A. Borrelli et al., “MAKES-QA: A multi-agent framework for knowledge graph construction and enrichment over scientific literature for question answering,” Expert Systems with Applications, 2026.
6. G. Chen and X. Liu, “A multi-agent collaborative framework for constructing knowledge graphs from text,” in Proc. IEEE Int. Conf. Knowledge Graph (ICKG), 2024.
7. D. Gao et al., “Self-evolving digital twins in flexible manufacturing: A large language model-powered multi-agent approach,” Digital Engineering, 2026.
8. W. Gong et al., “Harnessing collective intelligence of multi-agent LLM systems for sensor failure reasoning in smart manufacturing,” Journal of Industrial Information Integration, 2025.
9. X. Guan et al., “Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting,” in Proc. AAAI Conf. Artificial Intelligence, 2024.
10. S. Hatem et al., “Up to date: Automatic updating knowledge graphs using LLMs,” Procedia Computer Science, 2024.
11. D. H. Ho et al., “Leveraging multi-agent systems and large language models for diabetes knowledge graphs,” in Proc. IEEE Big Data, 2024.
12. X. Ji et al., “Lemad: LLM-empowered multi-agent system for anomaly detection in power grid services,” Electronics, 2025.
13. Z. Jia et al., “Enhancing multi-agent systems via reinforcement learning with LLM-based planner and graph-based policy,” in Proc. IEEE ICRA, 2025.
14. J. Jiang et al., “KG-Agent: An efficient autonomous agent framework for complex reasoning over knowledge graph,” in Proc. ACL, 2025.
15. I. Kazlaris et al., “From illusion to insight: A taxonomic survey of hallucination mitigation techniques in LLMs,” AI, 2025.
16. S. Knollmeyer, O. Caymazer, and D. Grossmann, “Document GraphRAG: Knowledge graph-enhanced retrieval augmented generation for document question answering within the manufacturing domain,” Electronics, 2025.
17. A. Kostka and J. Chudziak, “Synergizing logical reasoning, knowledge management and collaboration in multi-agent LLM system,” in Proc. PACLIC, 2024.
18. J. Li et al., “Agentic-KGR: Co-evolutionary knowledge graph construction through multi-agent reinforcement learning,” arXiv preprint, 2025.
19. Y. Li et al., “Harnessing diverse perspectives: A multi-agent framework for enhanced error detection in knowledge graphs,” in Proc. DASFAA, 2025.
20. G. Lian and H. Chan, “Industry-adaptive knowledge graph construction with multi-agent systems for cross-domain enterprise credit assessment,” in Proc. ICISAI, 2025.
21. S. Liang, Y. Zhang, and Y. Guo, “PersonaAgent with GraphRAG: Community-aware knowledge graphs for personalized LLM,” arXiv preprint, 2025.
22. J. Lin et al., “A multi-agent and synergistic knowledge graph retrieval-augmented generation framework for intelligent maintenance,” Journal of Manufacturing Systems, 2026.
23. X. Lin et al., “LLM-based agents suffer from hallucinations: A survey,” arXiv preprint, 2025.
24. Y. Liu et al., “Graph-augmented large language model agents: Current progress and future prospects,” arXiv preprint, 2025.
25. S. Lou et al., “A cognitive digital twin for Industry 5.0 based on a large language model agent,” in Proc. IEEE ICHMS, 2025.
26. W. Lu, Q. Wang, and Y. Zhao, “KARMA: Leveraging multi-agent LLMs for automated knowledge graph enrichment,” in Proc. NeurIPS, 2025.
27. E. Lumer et al., “Tool-to-agent retrieval: Bridging tools and agents for scalable LLM multi-agent systems,” arXiv preprint, 2025.
28. T. Mao et al., “A multi-agent framework for multi-source manufacturing knowledge integration and question answering,” in Proc. WWW Companion, 2025.
29. M. R. Martínez Rodríguez et al., “An LLM and embeddings-based multi-agentic system for knowledge graph construction and verification,” in Proc. PRIMA, 2025.
30. Y. Meng et al., “LLM and knowledge graph-based intelligent control framework for smart manufacturing,” in Proc. ASME IDETC, 2025.
31. T. Morioka, T. Kono, and T. Nishida, “Automatic construction of asset knowledge graph with large language model,” Procedia CIRP, 2025.
32. M. Muhtadi et al., “Adaptive self-prompting in agentic LLM frameworks for code fault detection,” Software, 2026.
33. R. Parekh et al., “Leveraging knowledge graphs and LLM reasoning to identify operational bottlenecks for warehouse planning assistance,” arXiv preprint, 2025.
34. J. Polonuer et al., “Autonomous knowledge graph exploration with adaptive breadth-depth retrieval,” arXiv preprint, 2026.
35. N. Pussadeniya et al., “CARA: A hybrid framework integrating swarm AI agents and knowledge graphs for advanced LLM reasoning,” in Proc. ICAC, 2024.
36. R. Saleh et al., “Self-evolving multi-agent network for industrial IoT predictive maintenance,” arXiv preprint, 2026.
37. S. Shao et al., “A medical consultation system for geriatric disease based on multi-agent architecture and knowledge graph,” in Proc. HIS, 2024.
38. W. Tang et al., “LLM-driven framework for knowledge graph construction, completion, and alignment,” in Proc. EIECS, 2025.
39. G. Tan et al., “LIDL: LLM integration defect localization via knowledge graph-enhanced multi-agent analysis,” arXiv preprint, 2026.
40. K. T. Tran et al., “Multi-agent collaboration mechanisms: A survey of LLMs,” arXiv preprint, 2025.
41. J. Wang et al., “Large language models-guided dynamic adaptation for temporal knowledge graph reasoning,” in Proc. NeurIPS, 2024.
42. Q. Wang et al., “Rethinking the bounds of LLM reasoning: Are multi-agent discussions the key?” in Proc. ACL, 2024.
43. X. Wang et al., “Multi-dimensional data analysis and applications based on LLM agents and knowledge graph interactions,” arXiv preprint, 2025.
44. T. Wu, J. Li, K. Bao, and Q. Liu, “ProcessCarbonAgent: A large language model-empowered autonomous agent for decision-making in manufacturing carbon emission management,” Journal of Manufacturing Systems, 2024.
45. T. Wu, J. Li, Q. Liu, and J. Bao, “CausalGID: Causality-guided Pareto generative design for industrial production with large language models,” Journal of Engineering Design, 2026.
46. Y. Xie et al., “KERAP: A knowledge-enhanced reasoning approach for accurate zero-shot diagnosis prediction using multi-agent LLMs,” arXiv preprint, 2025.
47. F. Yan et al., “An improved LLM and knowledge graph integration method for automated machining process base construction,” Journal of Manufacturing Systems, 2026.
48. J. Yu et al., “Dyntaskmas: A dynamic task graph-driven framework for asynchronous and parallel LLM-based multi-agent systems,” in Proc. ICAPS, 2025.
49. Y. Yun et al., “EICopilot: Search and explore enterprise information over large-scale knowledge graphs with LLM-driven agents,” in Proc. IEEE Big Data, 2025.
50. T. Zang et al., “Event-state knowledge graph-enhanced GraphRAG for order-driven 3D printing supply chain configuration,” Expert Systems with Applications, 2026.
51. J. Zhang et al., “CoMA-IKG: LLM-driven multi-agent framework for automated construction of industrial knowledge graph,” IEEE Transactions on Industrial Informatics, 2026.
52. Q. Zhang et al., “A survey of GraphRAG for customized large language models,” arXiv preprint, 2025.
53. Y. Zhang et al., “Automatic knowledge graph construction and dynamic fusion using LLMs and graph embedding for medical informatics education,” in Proc. CSEI, 2024.
54. Z. Zhao et al., “A large language model-based multi-agent manufacturing system for intelligent shopfloors,” Advanced Engineering Informatics, 2026.
55. J. Zhou, L. Wang, and X. Yang, “Guardian: Safeguarding LLM multi-agent collaborations with temporal graph modeling,” arXiv preprint, 2025.
56. Z. Zhou et al., “Synergizing LLM agents and knowledge graph for socioeconomic prediction in LBSN,” arXiv preprint, 2024.