ComposerX: Multi-Agent Symbolic Music Composition with LLMs
Abstract
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.
Cite
@article{arxiv.2404.18081,
title = {ComposerX: Multi-Agent Symbolic Music Composition with LLMs},
author = {Qixin Deng and Qikai Yang and Ruibin Yuan and Yipeng Huang and Yi Wang and Xubo Liu and Zeyue Tian and Jiahao Pan and Ge Zhang and Hanfeng Lin and Yizhi Li and Yinghao Ma and Jie Fu and Chenghua Lin and Emmanouil Benetos and Wenwu Wang and Guangyu Xia and Wei Xue and Yike Guo},
journal= {arXiv preprint arXiv:2404.18081},
year = {2024}
}