MuseAgent: Grounded Multimodal Understanding of Music Scores and Performance Audio

ACL ARR 2026 January Submission8912 Authors

Keywords: Multimodal Language Models, Music Understanding, Grounded Reasoning, Multimodal Agents, Symbolic Music, Benchmark

Abstract:

Despite recent advances in multimodal large language models (MLLMs), their ability to understand and interact with music remains limited. Music understanding requires grounded reasoning over symbolic scores and expressive performance audio, which general-purpose MLLMs often fail to handle due to insufficient perceptual grounding.
We introduce MuseAgent, a music-centric multimodal agent that augments language models with structured symbolic representations derived from sheet music images and performance audio. By integrating optical music recognition and automatic music transcription modules, MuseAgent enables multi-step reasoning and interaction over fine-grained musical content.
To systematically evaluate music understanding capabilities, we further propose MuseBench, a benchmark covering music theory reasoning, score interpretation, and performance-level analysis across text, image, and audio modalities. Experiments show that existing MLLMs perform poorly on these tasks, while MuseAgent achieves substantial improvements, highlighting the importance of structured multimodal grounding for interactive music understanding.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: multimodal learning, language grounding, multimodal agents, retrieval-augmented generation, benchmark, evaluation

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 8912