← Back to all news
arXiv AI By Haoyue Liu, Xiaoying Tang

Do Language Models Need Music Supervision? Verifiable Rewards for Multi-Constraint Symbolic Music Generation

Read the original on arXiv AI →

The paper introduces MusicConstraintBench, a benchmark of 2180 items testing symbolic music generation under multiple explicit constraints. It shows that current language models, such as Llama-3.1-70B, perform poorly on multi-constraint tasks, achieving only 4.4% success on four-constraint items. The authors propose MusicRLVR, a reinforcement learning approach that uses verifier rewards without human annotation, which significantly improves performance—raising Qwen3-4B-Instruct-2507’s success from 16% to 80.7% on mixed constraints after 300 updates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jun 9

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.

By Yirong Zeng, Yufei Liu, Xiao Ding, Yutai Hou, Yuxian Wang, Wu Ning, Haonan Song, Dandan Tu, Qixun Zhang, Yuxiang He, Bibo Cai, Ting Liu
llmsreinforcement-learningbenchmarkssafety
More like this →
arXiv AI
Jun 12

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.

By Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos
reinforcement-learningmultimodalbenchmarkssafety
More like this →
arXiv AI
Sep 1

TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models

TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.

By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh Manocha
llmsragreinforcement-learningfine-tuningmultimodalbenchmarks
More like this →