mlsanityData to 14 Oct 2026

MusicSwarm: Biologically Inspired Intelligence for Music Composition

arXiv 2509.11973 ↗First posted 15 Sep 2025cs.AI cs.MM cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compare a centralized multi-agent system with a global critic to a fully decentralized swarm in which bar-wise agents sense and deposit harmonic, rhythmic, and structural cues, adapt short-term memory, and reach consensus. Across symbolic, audio, and graph-theoretic analyses, the swarm yields superior quality while delivering greater diversity and structural variety and leads across creativity metrics. The dynamics contract toward a stable configuration of complementary roles, and self-similarity networks reveal a small-world architecture with efficient long-range connectivity and specialized bridging motifs, clarifying how local novelties consolidate into global musical form. By shifting specialization from parameter updates to interaction rules, shared memory, and dynamic consensus, MusicSwarm provides a compute- and data-efficient route to long-horizon creative structure that is immediately transferable beyond music to collaborative writing, design, and scientific discovery.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 88 references that are in the map. First posted on arXiv 15 Sep 2025.

Builds on

19 of 88 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  8. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 301
  9. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 184
  10. 2019Ripser: efficient computation of Vietoris-Rips persistence barcodescited by 117
  11. 2018Emergent Communication through Negotiationcited by 62
  12. 2020A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directionscited by 56
7 more
  1. 2019LakhNES: Improving multi-instrumental music generation with cross-domain pre-trainingcited by 54
  2. 2023MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalitiescited by 38
  3. 2017Music Generation by Deep Learning - Challenges and Directionscited by 24
  4. 2025Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principlescited by 17
  5. 2023ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion modelcited by 5
  6. 2017On the Complex Network Structure of Musical Pieces: Analysis of Some Use Cases from Different Music Genrescited by 2
  7. 2025Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoningcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Selective Imperfection as a Generative Framework for Analysis, Creativity and Discoverycited by 2