Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.12083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913893578702848 |
|---|---|
| author | Pandey, Amitesh Arifdjanov, Jafarbek Tiwari, Ansh |
| author_facet | Pandey, Amitesh Arifdjanov, Jafarbek Tiwari, Ansh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12083 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TuneGenie: Reasoning-based LLM agents for preferential music generation Pandey, Amitesh Arifdjanov, Jafarbek Tiwari, Ansh Sound Multiagent Systems Audio and Speech Processing I.2.6 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. |
| title | TuneGenie: Reasoning-based LLM agents for preferential music generation |
| topic | Sound Multiagent Systems Audio and Speech Processing I.2.6 |
| url | https://arxiv.org/abs/2506.12083 |