| title | Libretto: Giving LLM Agents a Sense of Musical Structure |
|---|---|
| authors | Yichen Xu |
| date | 2026-06-21 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.22708 |
| affiliation | University of California, Berkeley |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Generative music systems can now produce impressive audio from text prompts, but audio outputs are difficult to inspect, edit, and diagnose as musical structure. We introduce Libretto, an agent-facing framework for symbolic music generation and revision. Libretto uses an LLM-native grammar with explicit onset slots, voices, and bar-level organization, then evaluates each piece in a corpus-calibrated statistical space over rhythm, harmony, melody, texture, form, and variation. The same structural axes support retrieval, diagnosis, copy-risk control, and iterative self-revision. Across gap filling, reference-guided full-piece generation, gradual morphing, and educational music generation, Libretto turns symbolic music from a raw token sequence into a measurable and editable object for language-model agents. |
cite
@misc{xu2026libretto,
title={Libretto: Giving LLM Agents a Sense of Musical Structure},
author={Yichen Xu},
year={2026},
eprint={2606.22708},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.22708}
}