KA-RAG: Integrating Knowledge Graphs and Agentic Retrieval-Augmented Generation for an Intelligent Educational Question-Answering Model
Source abstract
Abstract
Generative artificial intelligence (AI) and large language models (LLMs) are reshaping the landscape of intelligent educational systems; however, existing solutions often suffer from unstructured resource organization, limited interpretability, and suboptimal retrieval precision. To address these challenges, this study introduces KA-RAG, a course-oriented question answering (QA) framework that integrates a structured Knowledge Graph (KG) with an Agentic Retrieval-Augmented Generation (Agentic-RAG) workflow. The system incorporates a responsive interface, a unified agent controller (ToolPlanner), a course knowledge graph, and a vector-based retrieval subsystem. By combining symbolic graph reasoning with dense semantic retrieval, the proposed dual-retrieval strategy supports interpretable, context-aware responses to course-related queries. Experiments conducted on a graduate-level Pattern Recognition course demonstrate that KA-RAG achieves a retrieval accuracy of 91.4%, semantic consistency of 87.6%, and an average response latency of 2.8 s. User surveys further reveal significant improvements in learning efficiency and satisfaction. The results validate the feasibility of integrating KG and Agentic-RAG techniques for knowledge-grounded educational applications, offering a practical pathway toward intelligent knowledge organization and interactive learning support.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Intelligent Tutoring Systems and Adaptive Learning · Advanced Graph Neural Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Hubei Key Laboratory of Intelligent Robot, School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China
Library, Wuhan Institute of Technology, Wuhan 430205, China
Funding
the National Natural Science Foundation of China · Academic Project of Hubei Provincial Library Society · Central Government Guides Local Science and Technology Development Special Projects · the National Natural Science Foundation of Hubei · Enterprise Technology Innovation Project · Academic Project of Wuhan Institute of Technolog
References (51)
Show source-provided references
1. A Review on the Use of Large Language Models as Virtual Tutors10.1007/s11191-024-00530-2 ↗
2. Application of Large Language Models in the Field of Education
3. Park, J.-H., Kim, S.-J., and Lee, S.-T. (2025). AI and Creativity in Entrepreneurship Education: A Systematic Review of LLM Applications. AI, 6.10.3390/ai6050100 ↗
4. Lai, C.H., Huang, J., and Chen, T. (2025). ITS-CAL: An Intelligent Tutoring System for Coding Powered by Large Language Models. Appl. Sci., 15.10.3390/app15041922 ↗
5. Zhou, X., Li, Y., Wang, Z., Zhang, C., Liu, P., Chen, X., Yang, F., Wu, Z., Li, H., and Zhang, W. (2025). Difficulty-Aware Programming Knowledge Tracing via Large Language Models. Sci. Rep., 15.10.1038/s41598-025-96540-3 ↗
6. Wang, T., Zhan, Y., Lian, J., Hu, Z., Yuan, N.J., Zhang, Q., Xie, X., and Xiong, H. (2025). LLM-Powered Multi-Agent Framework for Goal-Oriented Learning in Intelligent Tutoring Systems. arXiv.10.35542/osf.io/gt95h_v1 ↗
7. Gaeta, A., Weber, F., D’Angelo, G., Di Adamo, D., Persico, D., Pinto, M., Roselli, T., Sessa, S., Taibi, D., and Temperini, M. (2025, January 14–17). Enhancing Traditional Intelligent Tutoring Architectures with Large Language Models: Design and Evaluation. Proceedings of the International Conference on Information Systems (ICIS 2025), Nashville, TN, USA.
8. Rashtchian, C., and Juan, P. (2025, November 13). Deeper Insights into Retrieval-Augmented Generation: The Role of Sufficient Context. Google Research Blog. Available online: https://research.google/blog/deeper-insights-into-retrieval-augmented-generation-the-role-of-sufficient-context/.
9. Knowledge Graph Combined with Retrieval-Augmented Generation for Enhancing LMs Reasoning: A Survey10.54097/h21fky45 ↗
10. Retrieval-Augmented Generation (RAG)10.1007/s12599-025-00945-3 ↗
11. You, X., Luo, Y., and Gu, L. (2025, January 4–9). MS-RAG: Simple and Effective Multi-Semantic Retrieval-Augmented Generation. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China. Association for Computational Linguistics.10.18653/v1/2025.emnlp-main.1151 ↗
12. Yu, Y., Zhao, S., Wang, Z., Fan, M., Zhang, X., Zhang, Y., Zhengfan, W., Huang, H., and Liu, T. (2025, January 4–9). RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China. Association for Computational Linguistics.
13. Zhu, X., Xie, Y., Liu, Y., Li, Y., and Hu, W. (May, January 29). Knowledge Graph-Guided Retrieval-Augmented Generation. Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2025), Long Papers, Albuquerque, NM, USA.10.18653/v1/2025.naacl-long.449 ↗
14. Lu, T., Wang, F., and Huang, L. (2025). OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning. arXiv.
15. Osei Opoku, D., Sheng, M., and Zhang, Y. (2025). DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation. arXiv.10.36227/techrxiv.174837976.69904638/v1 ↗
16. An, B., Zhang, S., and Dredze, M. (2025). RAG LLMs Are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models. arXiv.10.18653/v1/2025.naacl-long.281 ↗
17. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
18. Karpukhin, V., Oguz, B., Min, S., Lewis, P.S., Wu, L., Edunov, S., Chen, D., and Yih, W.-t. (2020, January 16–20). Dense Passage Retrieval for Open-Domain Question Answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), Online.10.18653/v1/2020.emnlp-main.550 ↗
19. Guu, K., Lee, K., Tung, Z., Pasupat, P., and Chang, M.-W. (2020). REALM: Retrieval-Augmented Language Model Pre-Training. arXiv.
20. Izacard, G., and Grave, É. (2021, January 19–23). Leveraging Passage Retrieval with Generative Models for Open-Domain Question Answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Online.10.18653/v1/2021.eacl-main.74 ↗
21. RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
22. Jiang, Z., Ma, X., and Chen, W. (2024). LongRAG: Enhancing Retrieval-Augmented Generation with Long-Context LLMs. arXiv.
23. Translating Embeddings for Modeling Multi-Relational Data
24. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France.
25. Schlichtkrull, M., Kipf, T.N., Bloem, P., Van Den Berg, R., Titov, I., and Welling, M. (2018, January 3–7). Modeling Relational Data with Graph Convolutional Networks. Proceedings of the European Semantic Web Conference (ESWC), Crete, Greece.10.1007/978-3-319-93417-4_38 ↗
26. Li, L., and Wang, Z. (2023). Knowledge Graph Enhanced Intelligent Tutoring System Based on Exercise Representativeness and Informativeness. arXiv.10.1155/2023/2578286 ↗
27. Canal-Esteve, M., and Gutiérrez, Y. (2024). Educational Material to Knowledge Graph Conversion: A Methodology to Enhance Digital Education. Proceedings of the 1st Workshop on Knowledge-Augmented Language Models (KaLLM), Association for Computational Linguistics.10.18653/v1/2024.kallm-1.9 ↗
28. Qu, K., Li, K.C., Wong, B.T.M., Wu, M.M., and Liu, M. (2024). A Survey of Knowledge Graph Approaches and Applications in Education. Electronics, 13.10.3390/electronics13132537 ↗
29. Development of Knowledge Graph for University Courses Management
30. A Study on the Curriculum Design for K–12 AI Education Using Knowledge Graph
31. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K.R., and Cao, Y. (2022). ReAct: Synergizing Reasoning and Acting in Language Models. arXiv.
32. Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv.
33. Yu, D., Zhu, C., Fang, Y., Yu, W., Wang, S., Xu, Y., Ren, X., Yang, Y., and Zeng, M. (2021). KG-FiD: Infusing Knowledge Graphs into Fusion-in-Decoder. arXiv.10.18653/v1/2022.acl-long.340 ↗
34. Guu, K., Lee, K., and Tsvetkov, Y. (2023, January 23–29). Multimodal Retrieval-Augmented Learning for STEM Education. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA.
35. From Novice to Navigator: Students’ Help-Seeking Behavior and Perceived Usefulness of ChatGPT
36. Zhang, X., Zhang, Y., and Wang, Y. (2025). A Systematic Review of Key Retrieval-Augmented Generation Techniques. arXiv.
37. Chen, J., Liu, S., and Zhang, Z. (2025). LightRAG: Simple and Fast Retrieval-Augmented Generation. arXiv.
38. Gao, Y., Zhang, L., Liu, X., and Xu, C. (2023). A Systematic Review of Key Retrieval-Augmented Methods for Large Language Models. arXiv.
39. Henkel, O., Lindl, T., and Stöter, J. (2024, January 14–17). Retrieval-Augmented Generation to Improve Math Question Answering. Proceedings of the 18th International Conference on Educational Data Mining (EDM), Atlanta, GA, USA.
40. Graph Retrieval-Augmented Large Language Models for Rare Genetic Disease Diagnosis10.1038/s41746-025-01955-x ↗
41. Chen, S. (2025). AcademicRAG: Knowledge Graph Enhanced Retrieval-Augmented Generation for Academic Contexts. arXiv.
42. Review of Graph Neural Networks Applied to Knowledge Graph Reasoning
43. Bei, Y., Zhang, W., Wang, S., Chen, W., Zhou, S., Chen, H., Li, Y., Bu, J., Pan, S., and Yu, Y. (2025). Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities. arXiv.
44. Survey on the Construction Technology of Knowledge Graphs
45. Jiang, W., Zhang, M., and Li, Q. (2025). MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-Based Agentic Workflow. arXiv.10.1007/s00371-025-03946-1 ↗
46. Study on the Development History and Current Status of Semantic Networks
47. A Review of Ontology Research
48. Research on Smart Education Systems Driven by Knowledge Graphs
49. Educational Knowledge Graph: Research Progress and Future Development
50. The Semantic Web10.1038/scientificamerican0501-34 ↗
51. Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Models on Knowledge Graphs10.52202/079017-1189 ↗