MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models

TL;DR

MusicAgent is an AI system that leverages large language models to organize, automate, and simplify diverse music processing tasks, enabling users to focus on creativity without managing complex tools.

Contribution

The paper introduces MusicAgent, a novel system that integrates multiple music tools and uses LLMs to automate task decomposition and tool invocation for music understanding and generation.

Findings

Successfully integrates tools from multiple sources.

Automates task decomposition and tool invocation.

Enhances user experience by simplifying AI-music interactions.

Abstract

AI-empowered music processing is a diverse field that encompasses dozens of tasks, ranging from generation tasks (e.g., timbre synthesis) to comprehension tasks (e.g., music classification). For developers and amateurs, it is very difficult to grasp all of these task to satisfy their requirements in music processing, especially considering the huge differences in the representations of music data and the model applicability across platforms among various tasks. Consequently, it is necessary to build a system to organize and integrate these tasks, and thus help practitioners to automatically analyze their demand and call suitable tools as solutions to fulfill their requirements. Inspired by the recent success of large language models (LLMs) in task automation, we develop a system, named MusicAgent, which integrates numerous music-related tools and an autonomous workflow to address user requirements. More specifically, we build 1) toolset that collects tools from diverse sources, including Hugging Face, GitHub, and Web API, etc. 2) an autonomous workflow empowered by LLMs (e.g., ChatGPT) to organize these tools and automatically decompose user requests into multiple sub-tasks and invoke corresponding music tools. The primary goal of this system is to free users from the intricacies of AI-music tools, enabling them to concentrate on the creative aspect. By granting users the freedom to effortlessly combine tools, the system offers a seamless and enriching music experience.