LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering

• Ronald Carvalho Boadana UEA
• Ademir Guimarães da Costa Junior UEA
• Ricardo Rios UEA
• Fábio Santos da Silva UEA

DOI: https://doi.org/10.5753/eniac.2025.12422

Abstract

The growing availability of music on streaming platforms has led to information overload for users. To address this issue and enhance the user experience, increasingly sophisticated recommendation systems have been proposed. This work investigates the use of Large Language Models (LLMs) from the Gemini and LLaMA families, combined with intelligent agents, in a multi-agent personalized music recommendation system. The results are compared with a traditional content-based recommendation model, considering user satisfaction, novelty, and computational efficiency. LLMs achieved satisfaction rates of up to 89,32%, indicating their promising potential in music recommendation systems.

References

AWS (2025). Amazon web services. [link]. Acesso em: 13 mai. 2025.

CrewAI (2025). The leading multi-agent platform. [link]. Acesso em: 30 jun. 2025.

Docker (2025). Docker: Accelerated container application development. [link]. Acesso em: 30 jun. 2025.

Falah, Z. F. and Suryawan, F. (2022). Recommendation system to propose final project supervisors using cosine similarity matrix. Khazanah Informatika Jurnal Ilmu Komputer dan Informatika, 8(2).

Fiarni, C. and Maharani, H. (2019). Product recommendation system design using cosine similarity and content-based filtering methods. IJITEE (International Journal of Information Technology and Electrical Engineering), 3(2):42–48.

Fouad, O., Fouad, R., Hussen, N., and Abuhadrous, I. (2025). A comprehensive review of music recommendation systems. Adv. Sciences and Technology Journal, 2(1):1–18.

Gemini Team and Google DeepMind (2023). Gemini: A Family of Highly Capable Multimodal Models. arXiv preprint arXiv:2312.11805. Acesso em: 5 jun. 2025.

Google (2025). Gemini 2.0: Flash, Flash-Lite and Pro - Google Developers Blog. [link]. Acesso em: 28 mai.2025.

Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., and et al. (2024). The llama 3 herd of models.

Groq (2025). Groq is fast ai inference. [link]. Acesso em: 30 jun. 2025.

Kang, W.-C. and McAuley, J. (2018). Self-attentive sequential recommendation. In 2018 IEEE International Conference on Data Mining (ICDM), pages 197–206.

Maheshwari, C. (2023). Music recommendation on spotify using deep learning.

MongoDB (2025). Mongodb: The world’s leading modern database — mongodb. [link]. Acesso em: 30 jun. 2025.

Nguyen, H., Tran, N., Ly, D., Tran, A., Nguyen, A., Vo, H., et al. (2024). A model for song recommendation based on facial emotion analysis and musical emotion. International Journal of Intelligent Engineering & Systems, 17(4).

Russell, J. and Norvig, P. (2022). Artificial Intelligence - A Modern Approach. GEN LTC, 4th edition.

Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International Conference on World Wide Web, WWW ’01, page 285–295, New York, NY, USA. Association for Computing Machinery.

Schedl, M., Gómez, E., Urbano, J., et al. (2014). Music information retrieval: Recent developments and applications. Foundations and Trends® in Information Retrieval, 8(2-3):127–261.

Singh, R. H., Inderprastha Engineering College, AKTU, Maurya, S., Tripathi, T., Narula, T., Srivastav, G., Inderprastha Engineering College, AKTU, Inderprastha Engineering College, AKTU, Inderprastha Engineering College, AKTU, and Inderprastha Engineering College, AKTU (2020). Movie recommendation system using cosine similarity and KNN. Int. J. Eng. Adv. Technol., 9(5):556–559.

Sun, F., Liu, J., Wu, J., Pei, C., Lin, X., Ou, W., and Jiang, P. (2019). Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM ’19, page 1441–1450, New York, NY, USA. Association for Computing Machinery.

Vagliano, I., Galke, L., Mai, F., and Scherp, A. (2018). Using adversarial autoencoders for multi-modal automatic playlist continuation. In Proceedings of the ACM Recommender Systems Challenge 2018, RecSys Challenge ’18, New York, NY, USA. Association for Computing Machinery.

Yang, J. (2022). Personalized song recommendation system based on vocal characteristics. Mathematical Problems in Engineering, 2022(1):3605728.