ComposerX: Multi-Agent Symbolic Music Composition with LLMs
This addresses the challenge of creative music generation for AI applications, though it appears incremental as it builds on existing LLM capabilities with a multi-agent approach.
The authors tackled the problem of generating high-quality symbolic music compositions using LLMs, which often produce poor results despite advanced techniques. They introduced ComposerX, a multi-agent framework that significantly improved GPT-4's music composition quality, producing coherent polyphonic music with captivating melodies based on user instructions.
Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints. While demonstrating impressive capabilities in STEM subjects, current LLMs easily fail in this task, generating ill-written music even when equipped with modern techniques like In-Context-Learning and Chain-of-Thoughts. To further explore and enhance LLMs' potential in music composition by leveraging their reasoning ability and the large knowledge base in music history and theory, we propose ComposerX, an agent-based symbolic music generation framework. We find that applying a multi-agent approach significantly improves the music composition quality of GPT-4. The results demonstrate that ComposerX is capable of producing coherent polyphonic music compositions with captivating melodies, while adhering to user instructions.