Agentic AI Framework Using Retrieval Augmented Generation for Intelligent Academic Question Answering in Higher Education

Authors

  • Eko Aziz Apriadi Informatics Study Program, Universitas Indonesia Mandiri, South Lampung, Indonesia
  • Fathoni Dwi Atmoko Informatics Study Program, Universitas Indonesia Mandiri, South Lampung, Indonesia

DOI:

https://doi.org/10.32492/jeetech.v7i2.7214

Keywords:

Agentic AI, Retrieval-Augmented Generation, Academic question answering, Higher education, Intelligent academic services

Abstract

Universities require fast, consistent, and traceable academic information services, yet direct use of large language models still poses risks of hallucination, outdated knowledge, and unsupported answers. This study developed an Agentic Artificial Intelligence framework based on Retrieval-Augmented Generation for intelligent academic question answering. The study employed Design Science Research comprising problem identification, requirements analysis, architecture design, prototype implementation, retrieval benchmarking, and evaluation. The framework integrated an agent orchestrator, intent routing, query rewriting, hybrid retrieval, reranking, memory, policy guardrails, a generator, and a verifier to check grounding and answer sources. Controlled testing used 12 synthetic academic-policy documents and 216 questions covering course registration, payments, academic leave, graduation, theses, MBKM, scholarships, library services, LMS, transcripts, academic calendars, and administration. Baseline RAG achieved Hit@1 of 80.6%, Recall@3 of 93.5%, and MRR of 87.6%, whereas Agentic RAG achieved 96.3%, 99.5%, and 97.8%, respectively. The improvement mainly resulted from intent-aware query expansion and combined lexical-character retrieval, which improved handling of paraphrases and overlapping service terminology. The proposed framework offers a more structured, transparent, and auditable implementation pattern for AI-based academic services. Field evaluation using an institution’s official corpus remains necessary before operational deployment.

Downloads

Download data is not yet available.

References

Z. Li, Z. Wang, W. Wang, K. Hung, H. Xie, and F. L. Wang, “Retrieval-augmented generation for educational application: A systematic survey,” Computers and Education: Artificial Intelligence, vol. 8, Art. no. 100417, 2025, doi: 10.1016/j.caeai.2025.100417.

J. Swacha and M. Gracel, “Retrieval-Augmented Generation (RAG) Chatbots for Education: A Survey of Applications,” Applied Sciences, vol. 15, no. 8, Art. no. 4234, 2025, doi: 10.3390/app15084234.

L. Labadze, M. Grigolia, and L. Machaidze, “Role of AI chatbots in education: systematic literature review,” International Journal of Educational Technology in Higher Education, vol. 20, Art. no. 56, 2023, doi: 10.1186/s41239-023-00426-1.

C. McGrath, A. Farazouli, and T. Cerratto-Pargman, “Generative AI chatbots in higher education: a review of an emerging research area,” Higher Education, vol. 89, pp. 1533–1549, 2025, doi: 10.1007/s10734-024-01288-w.

M. I. Baig and E. Yadegaridehkordi, “ChatGPT in the higher education: A systematic literature review and research challenges,” International Journal of Educational Research, vol. 127, Art. no. 102411, 2024, doi: 10.1016/j.ijer.2024.102411.

R. Deng, M. Jiang, X. Yu, Y. Lu, and S. Liu, “Does ChatGPT enhance student learning? A systematic review and meta-analysis of experimental studies,” Computers & Education, vol. 227, Art. no. 105224, 2025, doi: 10.1016/j.compedu.2024.105224.

Y. Jin and L. Sercu, “ChatGPT Interventions in Higher Education: A Systematic Review of Experimental Studies,” Journal of Computer Assisted Learning, vol. 41, Art. no. e70072, 2025, doi: 10.1111/jcal.70072.

D. Yigci, M. Eryilmaz, A. K. Yetisen, S. Tasoglu, and A. Ozcan, “Large Language Model-Based Chatbots in Higher Education,” Advanced Intelligent Systems, vol. 7, no. 3, Art. no. 2400429, 2025, doi: 10.1002/aisy.202400429.

Y. Qian, “Pedagogical Applications of Generative AI in Higher Education: A Systematic Review of the Field,” TechTrends, vol. 69, pp. 1105–1120, 2025, doi: 10.1007/s11528-025-01100-1.

M. Belkina, S. Daniel, S. Nikolic, R. Haque, S. Lyden, P. Neal, S. Grundy, and G. M. Hassan, “Implementing generative AI (GenAI) in higher education: A systematic review of case studies,” Computers and Education: Artificial Intelligence, vol. 8, Art. no. 100407, 2025, doi: 10.1016/j.caeai.2025.100407.

R. M. Perez, M. Shimogawa, Y. Chang, X. Li, H. A. T. Phan, J. G. Marmorstein, E. S. K. Yanagawa, and E. J. Petersson, “Large language models for education: An open-source paradigm for automated Q&A in the graduate classroom,” Computers and Education: Artificial Intelligence, vol. 10, Art. no. 100546, 2026, doi: 10.1016/j.caeai.2026.100546.

S. Pozdniakov, J. Brazil, O. Poquet, S. Krusche, S. Berrezueta-Guzman, S. Sadiq, and H. Khosravi, “From knowledge gaps to learning opportunities: Leveraging student questions and dual use of generative AI to support student learning at scale,” Computers and Education: Artificial Intelligence, vol. 10, Art. no. 100509, 2026, doi: 10.1016/j.caeai.2025.100509.

L. Na Nongkhai, J. Wang, A. Wynn, and T. Mendori, “Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system,” Computers and Education: Artificial Intelligence, vol. 10, Art. no. 100526, 2026, doi: 10.1016/j.caeai.2025.100526.

N. Wang, D. Zou, H. Xie, and S. J. Qin, “A scoping review of generative AI-powered agentic AI in education: Research landscape, agentic capabilities, and insights from the frontier agent paradigm, exemplified by OpenClaw,” Computers and Education: Artificial Intelligence, vol. 11, Art. no. 100653, 2026, doi: 10.1016/j.caeai.2026.100653.

M. Abou Ali, F. Dornaika, and J. Charafeddine, “Agentic AI: a comprehensive survey of architectures, applications, and future directions,” Artificial Intelligence Review, vol. 59, Art. no. 11, 2026, doi: 10.1007/s10462-025-11422-4.

S. S. Chowa, R. Alvi, S. S. Rahman, et al., “From language to action: a review of large language models as autonomous agents and tool users,” Artificial Intelligence Review, vol. 59, Art. no. 71, 2026, doi: 10.1007/s10462-025-11471-9.

V. Gohil, S. B. Shah, K. Rauniyar, et al., “Towards safe and trustworthy agentic AI: foundations, taxonomy, technologies, applications, and future directions,” Artificial Intelligence Review, 2026, doi: 10.1007/s10462-026-11682-8.

L. Wang, C. Ma, X. Feng, et al., “A survey on large language model based autonomous agents,” Frontiers of Computer Science, vol. 18, Art. no. 186345, 2024, doi: 10.1007/s11704-024-40231-1.

S. Hosseini and H. Seilani, “The role of agentic AI in shaping a smart future: A systematic review,” Array, vol. 26, Art. no. 100399, 2025, doi: 10.1016/j.array.2025.100399.

A. Bandi, B. Kongari, R. Naguru, S. Pasnoor, and S. V. Vilipala, “The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges,” Future Internet, vol. 17, no. 9, Art. no. 404, 2025, doi: 10.3390/fi17090404.

S. Baradziej, “A systematic review of the roles of agentic AI in higher education,” Social Sciences & Humanities Open, vol. 14, Art. no. 103418, 2026, doi: 10.1016/j.ssaho.2026.103418.

X. Liu, Q. Tang, W. Wu, X. Chen, and C. Wang, “GenAI-agents in education: a systematic review of macro-level trends, educational roles, theoretical foundations and future agendas,” Interactive Learning Environments, 2026, doi: 10.1080/10494820.2026.2672562.

I. Pedersen, “AI agents, wearable computing and the future of postsecondary learning,” Frontiers in Education, vol. 10, Art. no. 1651453, 2025, doi: 10.3389/feduc.2025.1651453.

S. Wu, Y. Xiong, Y. Cui, et al., “Retrieval-augmented generation for natural language processing: a survey,” Artificial Intelligence Review, vol. 59, Art. no. 192, 2026, doi: 10.1007/s10462-026-11605-7.

X. Shu, X. Zhang, R. Wang, et al., “From knowledge retrieval to generation: a comprehensive study of RAG’s architectures, evolution, and applications,” Artificial Intelligence Review, 2026, doi: 10.1007/s10462-026-11716-1.

L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, and T. Liu, “A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions,” ACM Transactions on Information Systems, vol. 43, no. 2, Art. no. 42, pp. 1–55, 2025, doi: 10.1145/3703155.

I. Augenstein et al., “Factuality challenges in the era of large language models and opportunities for fact-checking,” Nature Machine Intelligence, vol. 6, pp. 852–863, 2024, doi: 10.1038/s42256-024-00881-z.

S. Knollmeyer, O. Caymazer, L. Koval, et al., “Evaluating Retrieval Augmented Generation: A Comprehensive Review of Evaluation Dimensions, Question Types, and Application,” SN Computer Science, vol. 7, Art. no. 576, 2026, doi: 10.1007/s42979-026-05134-x.

R. Julianto, T. Gunawan, and E. A. Apriadi, “Development of an Intelligent Educational Chatbot Using NLP and Machine Learning,” International Journal of Technology and Computer Science, vol. 1, no. 1, pp. 14–24, 2025, doi: 10.58290/ijtcs.v1i1.156.

Z. A. Hulmi and E. A. Apriadi, “Analysis of the Effect of Using Artificial Intelligence on Critical Thinking Power of Students in the Digital Age,” International Journal of Technology and Computer Science, vol. 1, no. 1, pp. 38–50, 2025, doi: 10.58290/ijtcs.v1i1.107.

Published

2026-11-16

How to Cite

[1]
Eko Aziz Apriadi and Fathoni Dwi Atmoko, “Agentic AI Framework Using Retrieval Augmented Generation for Intelligent Academic Question Answering in Higher Education”, jeetech, vol. 7, no. 2, pp. 337-352, Nov. 2026.