ComposerX: Multi-Agent Symbolic Music Composition with LLMs
On the map: LLM agents and tool use → Multimodal and embodied agents
Abstract (arXiv)
Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints. While demonstrating impressive capabilities in STEM subjects, current LLMs easily fail in this task, generating ill-written music even when equipped with modern techniques like In-Context-Learning and Chain-of-Thoughts. To further explore and enhance LLMs' potential in music composition by leveraging their reasoning ability and the large knowledge base in music history and theory, we propose ComposerX, an agent-based symbolic music generation framework. We find that applying a multi-agent approach significantly improves the music composition quality of GPT-4. The results demonstrate that ComposerX is capable of producing coherent polyphonic music compositions with captivating melodies, while adhering to user instructions.
Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 29 references that are in the map. First posted on arXiv 28 Apr 2024.
Builds on
21 of 29 references.
Closest ancestors · 1
Same direction, newest first
Other references · 20
- 2017Attention Is All You Needcited by 60,361
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2023Code Llama: Open Foundation Models for Codecited by 2,139
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2020Jukebox: A Generative Model for Musiccited by 542
- 2023Simple and Controllable Music Generationcited by 488
- 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
- 2023MusicLM: Generating Music From Textcited by 448
- 2024ChatMusician: Understanding and Generating Music Intrinsically with LLMcited by 68
- 2023SingSong: Generating musical accompaniments from singingcited by 55
8 more
- 2023MuseCoco: Generating Symbolic Music from Textcited by 52
- 2024MuPT: A Generative Symbolic Music Pretrained Transformercited by 33
- 2023Content-based Controls For Music Large Language Modelingcited by 19
- 2024Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controlscited by 17
- 2023Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editingcited by 15
- 2022Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Taskcited by 13
- 2022What is missing in deep music generation? A study of repetition and structure in popular musiccited by 11
- 2024ByteComposer: a Human-like Melody Composition Method based on Language Model Agentcited by 6
Built on by
Citing papers per year: 2024: 12; 2025: 21; 2026: 9.
42 papers.
Sort:
By area:
- 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
- 2024MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Seriescited by 67
- 2024AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Textcited by 42
- 2024VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modelingcited by 40
- 2024Foundation Models for Music: A Surveycited by 37
- 2024Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformerscited by 35
- 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agentcited by 33
- 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approachcited by 24
- 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMAcited by 23
- 2024Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustnesscited by 22
- 2024Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generationcited by 17
- 2024Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuningcited by 15
30 more
- 2024Data Imputation using Large Language Model to Accelerate Recommendation Systemcited by 15
- 2025Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environmentscited by 12
- 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editingcited by 12
- 2025Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learningcited by 11
- 2025Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healingcited by 10
- 2025Data Augmentation Through Random Style Replacementcited by 9
- 2025Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMscited by 9
- 2024Style Transfer: From Stitching to Neural Networkscited by 8
- 2025User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Datacited by 8
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
- 2024Creativity in AI: Progresses and Challengescited by 7
- 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systemscited by 6
- 2025FilmComposer: LLM-Driven Music Production for Silent Film Clipscited by 5
- 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generationcited by 5
- 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMscited by 5
- 2025ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversationcited by 4
- 2025Let Your Video Listen to Your Music!cited by 3
- 2025Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machinescited by 2
- 2025DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QAcited by 2
- 2025Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Modelscited by 1
- 2025CoComposer: LLM Multi-agent Collaborative Music Compositioncited by 1
- 2026How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptationcited by 1
- 2026Stemphonic: All-at-once Flexible Multi-stem Music Generationcited by 1
- 2026AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generationcited by 1
- 2025An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learningcited by 0
- 2025BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generationcited by 0
- 2026Exploring LLMs for South Asian Music Understanding and Generationcited by 0
- 2026Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Modelcited by 0
- 2026Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generationcited by 0
- 2026SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specificationscited by 0
- 2026SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications11 Oct 2026
- 2026Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation4 Aug 2026
- 2026Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model2 Jul 2026
- 2026AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation10 Jun 2026
- 2026Exploring LLMs for South Asian Music Understanding and Generation3 Jun 2026
- 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing12 Apr 2026
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agents5 Apr 2026
- 2026Stemphonic: All-at-once Flexible Multi-stem Music Generation10 Feb 2026
- 2026How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation30 Jan 2026
- 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA14 Dec 2025
- 2025BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation9 Sep 2025
- 2025CoComposer: LLM Multi-agent Collaborative Music Composition29 Aug 2025
30 more
- 2025Let Your Video Listen to Your Music!23 Jun 2025
- 2025Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models22 Jun 2025
- 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs13 Jun 2025
- 2025An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning9 Jun 2025
- 2025DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA31 May 2025
- 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation23 May 2025
- 2025Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs19 May 2025
- 2025Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healing16 May 2025
- 2025User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data8 May 2025
- 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent4 May 2025
- 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr 2025
- 2025Data Augmentation Through Random Style Replacement14 Apr 2025
- 2025Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machines28 Mar 2025
- 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems19 Mar 2025
- 2025Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments15 Mar 2025
- 2025Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning15 Mar 2025
- 2025FilmComposer: LLM-Driven Music Production for Silent Film Clips11 Mar 2025
- 2025ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation10 Mar 2025
- 2024Creativity in AI: Progresses and Challenges22 Oct 2024
- 2024AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text5 Oct 2024
- 2024Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation18 Sep 2024
- 2024Style Transfer: From Stitching to Neural Networks1 Sep 2024
- 2024Foundation Models for Music: A Survey26 Aug 2024
- 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach13 Aug 2024
- 2024Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness8 Aug 2024
- 2024Data Imputation using Large Language Model to Accelerate Recommendation System14 Jul 2024
- 2024Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers18 Jun 2024
- 2024VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling6 Jun 2024
- 2024MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series29 May 2024
- 2024Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning28 May 2024
- 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systemscited by 6
- 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generationcited by 5
- 2025DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QAcited by 2
- 2025DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA31 May 2025
- 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation23 May 2025
- 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems19 Mar 2025
- 2024Foundation Models for Music: A Surveycited by 37
- 2026AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generationcited by 1
- 2026AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation10 Jun 2026
- 2024Foundation Models for Music: A Survey26 Aug 2024
- 2024MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Seriescited by 67
- 2024AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Textcited by 42
- 2024VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modelingcited by 40
- 2024Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformerscited by 35
- 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approachcited by 24
- 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMAcited by 23
- 2024Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustnesscited by 22
- 2024Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuningcited by 15
- 2024Data Imputation using Large Language Model to Accelerate Recommendation Systemcited by 15
- 2025Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environmentscited by 12
- 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editingcited by 12
- 2025Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learningcited by 11
12 most cited of 30 All 30 (JSON)
- 2026Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation4 Aug 2026
- 2026Exploring LLMs for South Asian Music Understanding and Generation3 Jun 2026
- 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing12 Apr 2026
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agents5 Apr 2026
- 2026Stemphonic: All-at-once Flexible Multi-stem Music Generation10 Feb 2026
- 2026How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation30 Jan 2026
- 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA14 Dec 2025
- 2025BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation9 Sep 2025
- 2025Let Your Video Listen to Your Music!23 Jun 2025
- 2025Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models22 Jun 2025
- 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs13 Jun 2025
- 2025An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning9 Jun 2025
12 newest of 30 All 30 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2025An Agent-Based Framework for Automated Higher-Voice Harmony Generation
- 2026Libretto: Giving LLM Agents a Sense of Musical Structure
- 2025Artificial Intelligence Agents in Music Analysis: An Integrative Perspective Based on Two Use Cases
- 2024Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation
- 2025TuneGenie: Reasoning-based LLM agents for preferential music generation
- 2026Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation
- 2025CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning
- 2025NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms