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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boadana, Ronald Carvalho, Junior, Ademir Guimarães da Costa, Rios, Ricardo, da Silva, Fábio Santos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916902057541632
author Boadana, Ronald Carvalho
Junior, Ademir Guimarães da Costa
Rios, Ricardo
da Silva, Fábio Santos
author_facet Boadana, Ronald Carvalho
Junior, Ademir Guimarães da Costa
Rios, Ricardo
da Silva, Fábio Santos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering
Boadana, Ronald Carvalho
Junior, Ademir Guimarães da Costa
Rios, Ricardo
da Silva, Fábio Santos
Information Retrieval
Artificial Intelligence
Machine Learning
Multiagent Systems
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.
title LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering
topic Information Retrieval
Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2508.11671