LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering
This work addresses music recommendation for streaming platform users, but it is incremental as it applies existing LLMs to a known domain.
This paper tackled the problem of information overload in music streaming by comparing LLM-based intelligent agents with classical content-based filtering for music recommendation, achieving user satisfaction rates up to 89.32% with LLMs.
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 \textit{89{,}32\%}, indicating their promising potential in music recommendation systems.