Development of a Virtual Mentor Integrated with Retrieval-Augmented Generation Artificial Intelligence for Project-Based Learning

Dwi Soca Baskara; Nabil Muttaqin; Dio Lingga Purwodani

doi:10.32664/smatika.v16i01.2258

Authors

Dwi Soca Baskara Universitas Negeri Malang
Nabil Muttaqin Universitas Negeri Malang
Dio Lingga Purwodani Universitas Negeri Malang

DOI:

https://doi.org/10.32664/smatika.v16i01.2258

Keywords:

Artificial Intelligence, Higher Education, Project-Based Learning, Retrieval-Augmented Generation, Virtual Mentor

Abstract

Project-Based Learning (PjBL) is a learning model that can enhance the quality of higher education, particularly in developing critical thinking, creativity, and collaboration skills. However, implementing PjBL often faces challenges such as limited resources and the need for intensive guidance from lecturers. To overcome these challenges, Artificial Intelligence (AI) technology offers great potential, although traditional AI systems often provide responses that are less relevant to the context of the learning material. The Retrieval-Augmented Generation (RAG) technique in AI can serve as a solution, enabling the system to generate more accurate and contextually relevant responses. By utilizing data sources such as course materials, RAG can enhance the relevance of AI responses in supporting project-based learning. It is expected that developing an AI-based virtual mentor using the RAG approach can optimize students’ PjBL experiences. Specifically, this virtual mentor is designed to provide contextual guidance, help students overcome project-related challenges, and foster independent learning, thereby improving the quality and effectiveness of PjBL in higher education.

References

[1] A. Nurhadiyati, R. Rusdinal, and Y. Fitria, ‘Pengaruh Model Project Based Learning (PJBL) terhadap Hasil Belajar Siswa di Sekolah Dasar’, Jurnal Basicedu, vol. 5, no. 1, Art. no. 1, 2021, doi: 10.31004/basicedu.v5i1.684.

[2] N. Kamil, H. Sultan, and S. Ramadhan, ‘Bibliometric study: Project-based learning in education on learning outcomes Scopus publication 2021-2023’, Jurnal Inovasi dan Teknologi Pembelajaran, vol. 10, no. 2, Art. no. 2, Jul. 2023, doi: 10.17977/um031v10i22023p201.

[3] N. Fadlillah, M. Abdullah, and K. Kusaeri, ‘Exploring the Potential of Constructivist Pedagogical Approach in Strengthening Religious Moderation a Systematic Literature Review’, Scaffolding: Jurnal Pendidikan Islam dan Multikulturalisme, vol. 6, no. 1, Art. no. 1, Mar. 2024, doi: 10.37680/scaffolding.v6i1.4306.

[4] S. Gupta, R. Ranjan, and S. N. Singh, ‘A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions’, Oct. 03, 2024, arXiv: arXiv:2410.12837. doi: 10.48550/arXiv.2410.12837.

[5] 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, no. 100417, Jun. 2025, doi: 10.1016/j.caeai.2025.100417.

[6] R. Németh, A. Tátrai, M. Szabó, P. T. Zaletnyik, and Á. Tamási, ‘Exploring the use of retrieval-augmented generation models in higher education: A pilot study on artificial intelligence-based tutoring’, Social Sciences & Humanities Open, vol. 12, p. 101751, Jan. 2025, doi: 10.1016/j.ssaho.2025.101751.

[7] S. Prabhune and D. J. Berndt, ‘Deploying Large Language Models With Retrieval Augmented Generation’, Nov. 07, 2024, arXiv: arXiv:2411.11895. doi: 10.48550/arXiv.2411.11895.

[8] P. Zhao et al., ‘Retrieval-Augmented Generation for AI-Generated Content: A Survey’, Jun. 21, 2024, arXiv: arXiv:2402.19473. doi: 10.48550/arXiv.2402.19473.

[9] H. G. Sol, ‘Prototyping: A Methodological Assessment’, in Approaches to Prototyping, R. Budde, K. Kuhlenkamp, L. Mathiassen, and H. Züllighoven, Eds., Berlin, Heidelberg: Springer, 1984, pp. 368–382. doi: 10.1007/978-3-642-69796-8_31.

[10] M. G. Spiegel, ‘Prototyping: An approach to information and communication system design’, SIGMETRICS Perform. Eval. Rev., vol. 10, no. 1, pp. 9–19, Jan. 1981, doi: 10.1145/1010627.807904.

[11] A. Antika and E. Yulianingsih, ‘Analisa Sistem e-learning Pada Universitas PGRI Palembang Dengan Metode System Usability Scale (SUS)’, SMATIKA JURNAL, vol. 13, no. 01, pp. 53–61, Jun. 2023, doi: 10.32664/smatika.v13i01.721.

[12] Z. Liu, P. Agrawal, S. Singhal, V. Madaan, M. Kumar, and P. K. Verma, ‘LPITutor: an LLM based personalized intelligent tutoring system using RAG and prompt engineering’, PeerJ Comput. Sci., vol. 11, p. e2991, Aug. 2025, doi: 10.7717/peerj-cs.2991.