A Multi-Agent AI Framework for Musical Score Writing

Scott Josephson () and Atif Farid Mohammad ()
Additional contact information
Scott Josephson: Capitol Technology University, Maryland, USA
Atif Farid Mohammad: Capitol Technology University, Maryland, USA

RAIS Conference Proceedings 2022-2025 from Research Association for Interdisciplinary Studies

Abstract: The development of artificial intelligence (AI) has significantly influenced music composition, yet current single-agent AI systems face limitations in versatility, adaptability, and collaborative dynamics, often producing repetitive and stylistically rigid compositions. To address these challenges, this research proposes a multi-agent AI framework specifically designed for musical score writing, utilizing Agentic AI principles where autonomous, specialized agents collaboratively contribute elements such as melody, harmony, rhythm, and dynamics, emulating human compositional processes. Employing a mixed-method comparative design with quantitative assessments and qualitative evaluations by expert musicians, the study hypothesizes that multi-agent interactions enhance musical complexity, creativity, and coherence compared to single-agent systems. The expected findings aim to contribute significantly to computational creativity theory and practical applications in education, entertainment, and therapy, highlighting the potential of multi-agent systems to advance human-AI collaborative creativity.

Keywords: AI Agent; Computational Creativity; Multi-Agent Systems; Multimodal Large Language Model; Musical Score (search for similar items in EconPapers)
Pages: 12 pages
Date: 2025-11
References: Add references at CitEc
Citations:

Published in Proceedings of the 42nd International RAIS Conference on Social Sciences and Humanities, November 20-21, 2025, pages 198-210

Downloads: (external link)
https://rais.education/wp-content/uploads/0607.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:smo:raiswp:0607

Access Statistics for this paper

More papers in RAIS Conference Proceedings 2022-2025 from Research Association for Interdisciplinary Studies
Bibliographic data for series maintained by Eduard David ().