CoComposer: LLM Multi-agent Collaborative Music Composition
This work addresses the problem of limited duration, quality, and controllability in AI music composition for users needing more interpretable and editable tools, but it is incremental as it builds on existing multi-agent and LLM approaches.
The authors tackled limitations in AI music composition tools by introducing CoComposer, a multi-agent system based on traditional workflows, which outperforms existing multi-agent LLM-based systems in music quality and production complexity compared to single-agent systems, though it still lags behind non-LLM MusicLM in music quality.
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.