# CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning

arXiv: https://arxiv.org/abs/2601.11556 · HTML: https://mlsanity.com/paper/2601.11556/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 12 of 12)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix](https://mlsanity.com/paper/2505.13032/) (2025)
- [ChatMusician: Understanding and Generating Music Intrinsically with LLM](https://mlsanity.com/paper/2402.16153/) (2024)
- [Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents](https://mlsanity.com/paper/2405.16533/) (2024)
- [MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models](https://mlsanity.com/paper/2408.01337/) (2024)
- [MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models](https://mlsanity.com/paper/2310.11954/) (2023)
- [CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following](https://mlsanity.com/paper/2506.12285/) (2025)
- [The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2406.15885/) (2024)
- [WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning](https://mlsanity.com/paper/2509.04744/) (2025)
- [Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning](https://mlsanity.com/paper/2509.04059/) (2025)
- [Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machines](https://mlsanity.com/paper/2503.22853/) (2025)

## Built on by (most cited first, 2 of 2)

- [AMPS: Adaptive Modality Preference Steering via Functional Entropy](https://mlsanity.com/paper/2602.12533/) (2026)
- [ScorePrompts: Natural-Language Exploration of Symbolic Music Scores through Analysis](https://mlsanity.com/paper/2609.13291/) (2026)

## Abstract (arXiv)

Natural language information needs over symbolic music scores rarely reduce to a single step lookup. Many queries require compositional Music Information Retrieval (MIR) that extracts multiple pieces of evidence from structured notation and aggregates them to answer the question. This setting remains challenging for Large Language Models due to the mismatch between natural language intents and symbolic representations, as well as the difficulty of reliably handling long structured contexts. Existing benchmarks only partially capture these retrieval demands, often emphasizing isolated theoretical knowledge or simplified settings. We introduce CSyMR-Bench, a benchmark for compositional MIR in symbolic music reasoning grounded in authentic user scenarios. It contains 126 multiple choice questions curated from community discussions and professional examinations, where each item requires chaining multiple atomic analyses over a score to derive implicit musical evidence. To support diagnosis, we provide a taxonomy with six query intent categories and six analytical dimension tags. We further propose a tool-augmented retrieval and reasoning framework that integrates a ReAct-style controller with deterministic symbolic analysis operators built with music21. Experiments across prompting baselines and agent variants show that tool-grounded compositional retrieval consistently outperforms Large Language Model-only approaches, yielding 5-7% absolute accuracy gains, with the largest improvements on analysis-heavy categories.