dc.contributor.author | Deng, Q | en_US |
dc.contributor.author | Yang, Q | en_US |
dc.contributor.author | Yuan, R | en_US |
dc.contributor.author | Huang, Y | en_US |
dc.contributor.author | Wang, Y | en_US |
dc.contributor.author | Liu, X | en_US |
dc.contributor.author | Tian, Z | en_US |
dc.contributor.author | Pan, J | en_US |
dc.contributor.author | Zhang, G | en_US |
dc.contributor.author | Lin, H | en_US |
dc.contributor.author | Li, Y | en_US |
dc.contributor.author | Ma, Y | en_US |
dc.contributor.author | Fu, J | en_US |
dc.contributor.author | Lin, C | en_US |
dc.contributor.author | Benetos, E | en_US |
dc.contributor.author | Wang, W | en_US |
dc.contributor.author | Xia, G | en_US |
dc.contributor.author | Xue, W | en_US |
dc.contributor.author | Guo, Y | en_US |
dc.contributor.author | 25th International Society for Music Information Retrieval Conference (ISMIR), | en_US |
dc.date.accessioned | 2024-08-05T14:30:13Z | |
dc.date.available | 2024-06-28 | en_US |
dc.date.issued | 2024-11-10 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/98627 | |
dc.description.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. Current LLMs often struggle with this task, sometimes generating poorly 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. | en_US |
dc.rights | CC By | |
dc.title | ComposerX: Multi-Agent Symbolic Music Composition with LLMs | en_US |
dc.type | Conference Proceeding | |
pubs.notes | Not known | en_US |
pubs.publication-status | Accepted | en_US |
dcterms.dateAccepted | 2024-06-28 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | UKRI Centre for Doctoral Training in Artificial Intelligence and Music::Engineering and Physical Sciences Research Council | en_US |
qmul.funder | UKRI Centre for Doctoral Training in Artificial Intelligence and Music::Engineering and Physical Sciences Research Council | en_US |
rioxxterms.funder.project | b215eee3-195d-4c4f-a85d-169a4331c138 | en_US |