TuneGenie: Reasoning-based LLM agents for preferential music generation

TL;DR

TuneGenie leverages reasoning-based LLMs to analyze individual music preferences and generate prompts for AI music production, advancing personalized music creation through novel textual representations and benchmarking methods.

Contribution

Introduces TuneGenie, a novel LLM-based textual representation for music preference analysis and prompt generation, with new evaluation and benchmarking methods for AI music generation models.

Findings

TuneGenie effectively analyzes music preferences from various data sources.

The model generates high-quality prompts for AI music production.

Benchmarking methods provide new standards for evaluating AI music models.

Abstract

Recently, Large language models (LLMs) have shown great promise across a diversity of tasks, ranging from generating images to reasoning spatially. Considering their remarkable (and growing) textual reasoning capabilities, we investigate LLMs' potency in conducting analyses of an individual's preferences in music (based on playlist metadata, personal write-ups, etc.) and producing effective prompts (based on these analyses) to be passed to Suno AI (a generative AI tool for music production). Our proposition of a novel LLM-based textual representation to music model (which we call TuneGenie) and the various methods we develop to evaluate & benchmark similar models add to the increasing (and increasingly controversial) corpus of research on the use of AI in generating art.