Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
Abstract
Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe, its effect has never been measured in isolation. We fix pretrained Qwen3.5 (0.8B-27B), data, budget, and decoding, and swap only the representation across seven tokenizations, anchoring texture metrics to each representation's model-free ceiling. The ordering is clean and surprising: representation, not model size, is the binding variable for distributional fidelity. Scaling the backbone 34x barely moves Frechet Music Distance (FMD), whereas switching representation halves it. PMT, a performance-resolution stream we release (10 ms timing, per-note velocity, multi-track texture; 609 symbols), reaches FMD 159 at 0.8B against 272-286 for beat grids (1.7-1.8x lower, up to 2.8x elsewhere; non-overlapping bootstrap CIs), so a 0.8B performance-resolution model beats a 27B beat grid. It reappears on a 26M from-scratch backbone and a second performance-resolution tokenizer: a property of the class, not one lucky vocabulary. Nor is it a finer-lattice artifact: snapping PMT's onsets to the beat grids' resolution still leaves it 67-129 FMD ahead of both (n=500). The effect is distributional; whether it is audible is a separate question, left open by our probe, with a human study pre-registered. Native caption adherence is weak but separable: a lightweight decode-time constraint doubles instrument-F1 (.28 to .60) and Correct-Key (.16 to .35) at no distributional cost. We release the harness, 25+ checkpoints, two corpora (86.6k aligned across caption/MIDI/ABC/audio; 6.25M captioned, the largest for music), and an imprinting diagnostic: published text-to-MIDI systems reproduce their training distribution near-invariant to the caption (72% vs. 71% chord-time on disjoint domains). The field's next representation claim can now be measured, not asserted.
The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.
Research summary
The paper provides a rigorous, controlled evaluation demonstrating that token representation design is more critical than model scale for distributional fidelity in text-to-symbolic-music generation, supported by the release of new datasets and benchmarks.
Methodology
The paper proposes "PMT" (Performance-timed Music Tokens), a tokenization scheme for symbolic music generation that preserves 10ms micro-timing and per-note velocity, contrasting with traditional beat-grid tokenizations (like REMI) that quantize timing to metrical positions. The core methodological contribution is not just the tokenizer itself, but the rigorous "controlled swap" evaluation protocol. The authors fix the backbone (Qwen3.5, 0.8B-27B), data, training budget, and decoding strategy, varying only the tokenization scheme across seven different representations. This allows for an isolation of the representation's effect on distributional fidelity. The integration recipe involves vocabulary extension and caption-masked supervised fine-tuning. The approach is technically sound and addresses a significant confound in current music LLM research where representation, data, and model size are often entangled.
Results & evaluation
The experimental design is the strongest aspect of the paper. By controlling for model scale and data, the authors demonstrate that representation quality dominates model size for distributional fidelity (measured by Fréchet Music Distance). A 0.8B model using PMT outperforms a 27B model using beat grids. They further validate this on a 26M parameter from-scratch backbone and a second performance-resolution tokenizer (PerTok), suggesting the result is a property of the representation class. They also provide an "imprinting diagnostic" showing that existing systems (MIDI-LLM, text2midi) reproduce training distributions rather than following captions, highlighting a limitation in current text-conditioned symbolic generation. The release of two large datasets (86.6k aligned, 6.25M captioned) and a benchmark harness adds substantial empirical value.
Reproducibility
High. The authors release the PMT tokenizer, the evaluation harness, 25+ checkpoints, and the datasets. The controlled swap protocol is clearly defined, allowing other researchers to replicate the comparison. The use of standard backbones (Qwen3.5) and open metrics (FMD) further aids reproducibility.
Limitations
The paper explicitly acknowledges that the distributional fidelity gains do not necessarily translate to perceptual/audible quality, which is left for a pre-registered human study. Additionally, caption adherence (e.g., key, instrument) is weak for PMT compared to dedicated systems, although the authors show a lightweight decode-time constraint can mitigate this. The "imprinting" finding suggests a broader issue with text-conditioned symbolic generation that may require architectural changes beyond tokenization to fully resolve. The lack of explicit institution names in the provided text makes institutional assessment difficult, though the technical content is strong.
Broader impact
This work has significant implications for the field of symbolic music generation and potentially other structured artifact generation domains (e.g., code, 3D assets). It challenges the assumption that scaling models alone will solve quality issues, emphasizing the critical role of representation design. The release of large, high-quality datasets and benchmarks will facilitate future research. The finding that representations can dominate scale is a crucial lesson for efficient model development. The paper provides a rigorous, controlled evaluation demonstrating that token representation design is more critical than model scale for distributional fidelity in text-to-symbolic-music generation, supported by the release of new datasets and benchmarks.
Author of this paper? Send a correction.