홈 › Papers

ComposerX: Multi-Agent Symbolic Music Composition with LLMs

2024-04-28 · Qixin Deng, Qikai Yang, Ruibin Yuan, Yipeng Huang, Yi Wang, Xubo Liu, Zeyue Tian, Jiahao Pan, Ge Zhang, Hanfeng Lin, Yizhi Li, Yinghao Ma, Jie Fu, Chenghua Lin, Emmanouil Benetos, Wenwu Wang, Guangyu Xia, Wei Xue, Yike Guo

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.

📄 PDF Abstract BibTeX arXiv:2404.18081

Code (1)

lllindsey0615/composerx 공식 구현

Tasks

In-Context LearningMusic Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Position-Wise Feed-Forward Layer 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning

2025-12-16 · Boyang Wang, Yash Vishe, Xin Xu, Zachary Novack 외 arxiv

Natural language information needs over symbolic music scores rarely reduce to a single step lookup. Many queries require compositional Music Information Retrieval (MIR) that extracts multiple pieces of evidence from str…

Information Retrieval

An Agent-Based Framework for Automated Higher-Voice Harmony Generation

2025-09-29 · Nia D'Souza Ganapathy, Arul Selvamani Shaja arxiv

The generation of musically coherent and aesthetically pleasing harmony remains a significant challenge in the field of algorithmic composition. This paper introduces an innovative Agentic AI-enabled Higher Harmony Music…

ByteComposer: a Human-like Melody Composition Method based on Language Model Agent

2024-02-24 · Xia Liang, Xingjian Du, Jiaju Lin, Pei Zou 외

Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To…

Language Modeling Language Modelling Music Generation

WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

2025-09-05 · Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu 외 arxiv

Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remai…

Question Answering

MusicSwarm: Biologically Inspired Intelligence for Music Composition

2025-09-15 · Markus J. Buehler arxiv

We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compa…