EduMSRA: A Multi-Source Educational Research Agent Integrating Retrieval-Augmented Generation and Model Context Protocol for Adaptive Intelligent Tutoring Systems
Source abstract
Abstract
The integration of Artificial Intelligence into educational systems has accelerated dramatically with the advent of Large Language Models (LLMs). However, two critical limitations constrain current AI-powered tutoring systems: LLMs hallucinate factually incorrect content in high-stakes pedagogical contexts, and existing systems lack standardized mechanisms to dynamically access and synthesize knowledge from heterogeneous educational sources, including learning management systems, open-access textbook repositories, assessment databases, and real-time educational APIs. This paper presents a systematic survey of the convergence of Retrieval-Augmented Generation (RAG) and the Model Context Protocol (MCP) in educational AI applications. Based on our taxonomy, we identify a critical architectural gap: no current system simultaneously achieves multi-source curriculum retrieval, standardized tool orchestration, learner-adaptive personalization, and citation-aware generation within a unified framework. To address this, we propose EduMSRA (Educational Multi-Source Research Agent)—a novel architecture comprising a Hierarchical Educational RAG Pipeline, an MCP-based Curriculum Tool Orchestration Layer, a Conflict-Aware Fusion Module (CAFM), a Learner Profile Manager (LPM), and a Pedagogical Policy Agent (PPA) aligned with Bloom’s taxonomy. We further provide a comprehensive experimental design road map specifying nine publicly available benchmark datasets and four evaluation experiments. Additionally, we conduct three Bayesian empirical analyses: (1) a random-effects meta-analysis of 12 RAG studies indicating a positive effect direction (μ^=0.511, 95% HDI: [0.250,0.790]), I2=99.3% heterogeneity flagged as indicative), (2) a BKT simulation illustrating adaptive scaffolding dynamics across five learner profiles, and (3) a Beta-Binomial difficulty characterization of nine benchmark datasets. Our analysis demonstrates that EduMSRA offers a principled, scalable path toward adaptive, grounded, and pedagogically aligned AI tutoring agents.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Intelligent Tutoring Systems and Adaptive Learning · Text Readability and Simplification · Topic Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Natural Language Processing and Knowledge Discovery Research Group, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh 700000, Vietnam
Faculty of Management Information Systems, Ho Chi Minh University of Banking (HUB), Ho Chi Minh 700000, Vietnam
References (82)
Show source-provided references
1. The 2 Sigma Problem: The Search for Methods of Group Instruction as Effective as One-to-One Tutoring10.3102/0013189X013006004 ↗
2. Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge10.1007/BF01099821 ↗
3. The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutoring Systems10.1080/00461520.2011.611369 ↗
4. LPITutor: An LLM Based Personalized Intelligent Tutoring System Using RAG and Prompt Engineering10.7717/peerj-cs.2991 ↗
5. ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education10.1016/j.lindif.2023.102274 ↗
6. Modran, H.A. (2025). Leveraging RAG with ACP & MCP for Adaptive Intelligent Tutoring. Appl. Sci., 15.10.3390/app152111443 ↗
7. Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Review10.1111/bjet.13370 ↗
8. Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., and Qin, B. (2023). A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. arXiv.
9. Survey of Hallucination in Natural Language Generation10.1145/3571730 ↗
10. Tonmoy, S., Zaman, S., Jain, V., Rani, A., Rawber, A., Chadha, A., and Das, A. (2024). A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models. arXiv.
11. Swacha, J., and Gracel, M. (2025). Retrieval-Augmented Generation (RAG) Chatbots for Education: A Survey of Applications. Appl. Sci., 15.10.3390/app15084234 ↗
12. Anthropic (2024). Introducing the Model Context Protocol, Anthropic. Technical Report.
13. Hou, X., Zhao, Y., Wang, S., and Wang, H. (2025). Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions. arXiv.10.1145/3796519 ↗
14. Anderson, L., and Krathwohl, D. (2001). A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives, Longman.
15. Bloom, B. (1956). Taxonomy of Educational Objectives: The Classification of Educational Goals, Longmans, Green and Co.
16. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., and Rocktäschel, T. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv.
17. Retrieval-Augmented Generation for Educational Application: A Systematic Survey10.1016/j.caeai.2025.100417 ↗
18. Jeong, S., Baek, J., Cho, S., Hwang, S.J., and Park, J.C. (2024). Adaptive-RAG: Learning to Adapt Retrieval-Augmented LLMs through Question Complexity. arXiv.10.18653/v1/2024.naacl-long.389 ↗
19. Asai, A., Wu, Z., Wang, Y., Sil, A., and Hajishirzi, H. (2024). Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. arXiv.
20. Singh, A., Ehtesham, A., Kumar, S., Khoei, T.T., and Vasilakos, A.V. (2025). Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG. arXiv.
21. Trivedi, H., Balasubramanian, N., Khot, T., and Sabharwal, A. (2023). Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. arXiv.10.18653/v1/2023.acl-long.557 ↗
22. Jiang, J., Chen, J., Li, J., Ren, R., Wang, S., Zhao, W.X., Song, Y., and Zhang, T. (2024). RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement. arXiv.10.18653/v1/2025.naacl-long.361 ↗
23. Luo, Z., Shen, Z., Yang, W., Zhao, Z., Jwalapuram, P., Saha, A., Sahoo, D., Savarese, S., Xiong, C., and Li, J. (2025). MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers. arXiv.
24. Fan, S., Ding, X., Zhang, L., and Mo, L. (2025). MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark. arXiv.
25. Wang, Z., Chang, Q., Patel, H., Biju, S., Wu, C., Liu, Q., Ding, A., Rezazadeh, A., Shah, A., and Bao, Y. (2025). MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers. arXiv.
26. Zhang, D., Li, Z., Luo, X., Liu, X., Li, P., and Xu, W. (2025). MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents. arXiv.
27. Radosevich, B., and Halloran, J. (2025). MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits. arXiv.
28. Vygotsky, L.S. (1978). Mind in Society: The Development of Higher Psychological Processes, Harvard University Press.
29. Scarlatos, A., Baker, R.S., and Lan, A. (2024). Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs. arXiv.10.1145/3706468.3706501 ↗
30. Cui, J., Qian, H., Jiang, B., and Zhang, W. (2024). Leveraging Pedagogical Theories to Understand Student Learning Process with Graph-based Reasonable Knowledge Tracing. arXiv.10.1145/3637528.3671853 ↗
31. Liu, V., Latif, E., and Zhai, X. (2025). Advancing Education through Tutoring Systems: A Systematic Literature Review. arXiv.
32. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. arXiv.
33. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (2022). Training Language Models to Follow Instructions with Human Feedback. arXiv.
34. Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., and Yih, W. (2020). Dense Passage Retrieval for Open-Domain Question Answering. arXiv.10.18653/v1/2020.emnlp-main.550 ↗
35. Guu, K., Lee, K., Tung, Z., Pasupat, P., and Chang, M. (2020). Retrieval Augmented Language Model Pre-Training. arXiv.
36. Izacard, G., and Grave, E. (2021). Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. arXiv.10.18653/v1/2021.eacl-main.74 ↗
37. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J.B., Damoc, B., and Clark, A. (2022). Improving Language Models by Retrieving from Trillions of Tokens. arXiv.
38. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., and Wang, H. (2024). Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv.
39. Jiang, Z., Xu, F., Gao, L., Sun, Z., Liu, Q., Dwivedi-Yu, J., Yang, Y., Callan, J., and Neubig, G. (2023). Active Retrieval Augmented Generation. arXiv.10.18653/v1/2023.emnlp-main.495 ↗
40. Yan, S.-Q., Gu, J.-C., Zhu, Y., and Ling, Z.-H. (2024). Corrective Retrieval Augmented Generation (CRAG). arXiv.10.2139/ssrn.5267341 ↗
41. Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2024). Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv.
42. Towards Personalized AI Education: Context-Aware RAG With Grade-Level LLM Adaptation10.1002/cae.70153 ↗
43. Levonian, Z., Li, C., Zhu, W., Gade, A., Henkel, O., Postle, M.E., and Xing, W. (2023, January 15). Retrieval-Augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference. Proceedings of the NeurIPS 2023 Workshop on Generative AI for Education (GAIED), New Orleans, LA, USA.
44. Graesser, A.C., D’Mello, S., Hu, X., Cai, Z., Olney, A., and Morgan, B. (2012). AutoTutor. Applied Natural Language Processing: Identification, Investigation and Resolution, IGI Global.10.4018/978-1-60960-741-8.ch010 ↗
45. Wampler, D., Nielson, D., and Seddighi, A. (2025). Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems. arXiv.
46. Singh, A., Ehtesham, A., Kumar, S., and Khoei, T.T. (2025). A Survey of the Model Context Protocol (MCP): Standardizing Context to Enhance LLMs. Preprints, 2025040245.10.20944/preprints202504.0245.v1 ↗
47. Fei, X., Zheng, X., and Feng, H. (2025). MCP-Zero: Active Tool Discovery for Autonomous LLM Agents. arXiv.
48. Lumer, E., Gulati, A., Subbiah, V., Basavaraju, P., and Burke, J. (2025). ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents. arXiv.10.1007/978-3-032-15632-7_2 ↗
49. Hasan, M., Li, H., Rajbahadur, G., Adams, B., and Hassan, A. (2026). Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions. arXiv.
50. Li, Q., and Xie, Y. (2025). From Glue-Code to Protocols: A Critical Analysis of A2A and MCP Integration for Scalable Agent Systems. arXiv.
51. Ehtesham, A., Singh, A., Gupta, G., and Kumar, S. (2025). A Survey of Agent Interoperability Protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP). arXiv.
52. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020). Language Models are Few-Shot Learners. arXiv.
53. Zhu, X., Chang, S., and Kuik, A. (2025). Enhancing Critical Thinking with AI: A Tailored Warning System for RAG Models. arXiv.
54. Shi, W., Min, S., Yasunaga, M., Seo, M., James, R., Lewis, M., Zettlemoyer, L., and Yih, W. (2024). REPLUG: Retrieval-Augmented Black-Box Language Models. arXiv.10.18653/v1/2024.naacl-long.463 ↗
55. In-Context Retrieval-Augmented Language Models10.1162/tacl_a_00605 ↗
56. Ma, X., Gong, Y., He, P., Zhao, H., and Duan, N. (2023). Query Rewriting in Retrieval-Augmented Large Language Models. arXiv.10.18653/v1/2023.emnlp-main.322 ↗
57. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. arXiv.
58. Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., and Yao, S. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. arXiv.10.52202/075280-0377 ↗
59. Chen, Y., Yan, L., Sun, W., Ma, X., Zhang, Y., Wang, S., Yin, D., Yang, Y., and Mao, J. (2025). Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning. arXiv.
60. Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., and Lin, Y. (2024). A Survey on Large Language Model Based Autonomous Agents. Front. Comput. Sci., 18.10.1007/s11704-024-40231-1 ↗
61. Aghajani Asl, M., Asgari-Bidhendi, M., and Minaei-Bidgoli, B. (2025). FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation. arXiv.
62. Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., and Wen, J.-R. (2024). A Survey on the Memory Mechanism of Large Language Model Based Agents. arXiv.
63. Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., Metropolitansky, D., Ness, R.O., and Larson, J. (2025). From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv.
64. Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., and Manning, C.D. (2024). RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval. arXiv.
65. Baek, J., Aji, A., and Saffari, A. (2024). Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering. arXiv.10.18653/v1/2023.nlrse-1.7 ↗
66. Es, S., James, J., Espinosa-Anke, L., and Schockaert, S. (2024). RAGAS: Automated Evaluation of Retrieval Augmented Generation. arXiv.10.18653/v1/2024.eacl-demo.16 ↗
67. Chen, J., Lin, H., Han, X., and Sun, L. (2024). Benchmarking Large Language Models in Retrieval-Augmented Generation. arXiv.10.1609/aaai.v38i16.29728 ↗
68. Abootorabi, M.M., Zobeiri, A., Dehghani, M., Mohammadkhani, M., Mohammadi, B., Ghahroodi, O., Soleymani Baghshah, M., and Asgari, E. (2025). Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation. arXiv.10.18653/v1/2025.findings-acl.861 ↗
69. Lu, P., Mishra, S., Xia, T., Qiu, L., Chang, K.-W., Zhu, S.-C., Tafjord, O., Clark, P., and Kalyan, A. (2022). Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering. arXiv.
70. Ray, P. (2025). A Survey on Model Context Protocol: Architecture, State-of-the-Art, Challenges. TechRxiv, TechRxiv:174495492.22752319.10.36227/techrxiv.174495492.22752319/v1 ↗
71. Liu, W., Liu, Z., Dai, E., Yu, W., Yu, L., Yang, T., Han, J., and Gao, H. (2025). MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use. arXiv.
72. Wang, W., Niu, P., Xu, Z., Chen, Z., Du, J., Du, Y., Pang, X., Huang, K., Wang, Y., and Yan, Q. (2025). MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools. arXiv.
73. Nie, X., Guo, Z., Chen, Y., Zhou, Y., and Zhang, W. (2026). AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents. arXiv.
74. Intelligent Tutoring Systems: A Systematic Review of Characteristics, Applications, and Evaluation Methods10.1080/10494820.2018.1558257 ↗
75. Khan Academy (2026, March 15). Khanmigo: AI-Powered Teaching and Learning Assistant. Available online: https://www.khanmigo.ai/.
76. Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. (2021). Measuring Massive Multitask Language Understanding (MMLU). arXiv.
77. Wan, Y., Liu, Y., Ajith, A., Grazian, C., Hoex, B., Zhang, W., Kit, C., Xie, T., and Foster, I. (2024). SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation. arXiv.
78. Measuring Inconsistency in Meta-analyses10.1136/bmj.327.7414.557 ↗
79. GISedu-GPT: A Large Language Model Framework with Prior Knowledge for GIS Education10.1080/03098265.2025.2549784 ↗
80. GeoGPT: An Assistant for Understanding and Processing Geospatial Tasks
81. Jahanbakhsh, N., Vega-Barbas, M., Pau, I., Elvira-Martín, L., Moosavi, H., and García-Vázquez, C. (2025). Leveraging RAG for Automated Smart Home Orchestration. Future Internet, 17.10.3390/fi17050198 ↗
82. James, A., Trovati, M., and Bolton, S. (2025). RAG to Generate Knowledge Assets and Creation of Action Drivers. Appl. Sci., 15.10.3390/app15116247 ↗