# CoComposer: LLM Multi-agent Collaborative Music Composition

**Authors:** Peiwen Xing, Aske Plaat, Niki van Stein

arXiv: 2509.00132 · 2025-09-03

## TL;DR

CoComposer is a multi-agent AI system that enhances music composition by improving quality, controllability, and complexity through collaboration of specialized agents, outperforming existing multi-agent systems.

## Contribution

Introduces CoComposer, a multi-agent system with five collaborating agents based on traditional workflows, evaluated with multiple LLMs, demonstrating superior music quality and complexity.

## Key findings

- Outperforms existing multi-agent LLM systems in music quality.
- Achieves higher production complexity than single-agent systems.
- Offers better interpretability and editability than non-LLM MusicLM.

## Abstract

Existing AI Music composition tools are limited in generation duration, musical quality, and controllability. We introduce CoComposer, a multi-agent system that consists of five collaborating agents, each with a task based on the traditional music composition workflow. Using the AudioBox-Aesthetics system, we experimentally evaluate CoComposer on four compositional criteria. We test with three LLMs (GPT-4o, DeepSeek-V3-0324, Gemini-2.5-Flash), and find (1) that CoComposer outperforms existing multi-agent LLM-based systems in music quality, and (2) compared to a single-agent system, in production complexity. Compared to non- LLM MusicLM, CoComposer has better interpretability and editability, although MusicLM still produces better music.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/2509.00132/full.md

## References

23 references — full list in the complete paper: https://tomesphere.com/paper/2509.00132/full.md

---
Source: https://tomesphere.com/paper/2509.00132