Artificial Intelligence Agents in Music Analysis: An Integrative Perspective Based on Two Use Cases
Antonio Manuel Martínez-Heredia, Dolores Godrid Rodríguez, Andrés Ortiz García
TL;DR
This paper addresses how AI agents can advance music analysis and education by integrating historical rule-based methods, MIR, deep learning, RAG, and multi-agent architectures. It proposes a dual-case methodology: (i) a pedagogical study using generative AI tools in secondary education to enhance analytical and creative skills, and (ii) a technical multi-agent system for symbolic music analysis of an 18th-century repertoire. The study demonstrates that AI agents improve pattern recognition, compositional parameterization, and educational feedback, while also highlighting challenges in transparency, bias, and evaluation metrics. The work offers an evidence-based framework for designing responsible, interpretable AI tools in computational musicology and music education, with practical implications for researchers, educators, and developers.
Abstract
This paper presents an integrative review and experimental validation of artificial intelligence (AI) agents applied to music analysis and education. We synthesize the historical evolution from rule-based models to contemporary approaches involving deep learning, multi-agent architectures, and retrieval-augmented generation (RAG) frameworks. The pedagogical implications are evaluated through a dual-case methodology: (1) the use of generative AI platforms in secondary education to foster analytical and creative skills; (2) the design of a multiagent system for symbolic music analysis, enabling modular, scalable, and explainable workflows. Experimental results demonstrate that AI agents effectively enhance musical pattern recognition, compositional parameterization, and educational feedback, outperforming traditional automated methods in terms of interpretability and adaptability. The findings highlight key challenges concerning transparency, cultural bias, and the definition of hybrid evaluation metrics, emphasizing the need for responsible deployment of AI in educational environments. This research contributes to a unified framework that bridges technical, pedagogical, and ethical considerations, offering evidence-based guidance for the design and application of intelligent agents in computational musicology and music education.