MusicSwarm: Biologically Inspired Intelligence for Music Composition
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117
Network ‘Small-World-Ness’: A Quantitative Method for Determining Canonical Network Equivalence
Humphries, M. D., & Gurney, K. (2008) · PLoS ONE · doi:10.1371/journal.pone.0002051 · Cited by 1,442 · cited 1×
“To assess small-world structure, we calculated the Watts – Strogatz small-worldness index σ = ( C / C rand )/( L / L rand ) [99], where C and L are clustering and path length of the empirical graph and C rand and L rand are the corresponding averages from Erd ő s – Rényi graphs with the same n and…”
Multiagent systems: A survey from a machine learning perspective
Stone, P., & Veloso, M. (2000) · Autonomous Robots · doi:10.1023/a:1008942012299 · Cited by 1,218 · cited 1×
“Instead of relying on massive parameter updates across entire neural networks, multi-agent systems enable specialized agents to develop distinct competencies while learning to coordinate through environmental interactions and peer feedback [53, 54].”
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087
ReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Zelikman, E., Harik, G., Shao, Y., Jayasiri, V., Haber, N., & Goodman, N. D. (2024) · arXiv · doi:10.48550/arxiv.2403.09629 · Cited by 16 · cited 1×
“…currently widely used strategies (e.g., pretraining followed by task-specific fine-tuning, RLHF-style alignment, or test-time compute) [2, 3, 5, 25 – 29], in this study, we revisit early traditions of distributed cognition, such as Minsky ’ s Society of Mind and the rule-based MYCIN expert…”
Research works printed but not linked: 97
- Vaswani A., 2017, Advances in Neural Information Processing Systems
- D. M.Ziegler N.Stiennon J.Wu et al. ”Fine‐Tuning Language Models From Human Preferences ” arXiv preprint arXiv:1909.08593 2020 https://arxiv.org/abs/1909.08593. · arXiv
- 10.1038/s42256‐024‐00918‐3 · DOI
- 10.1115/1.4063843 · DOI · Paper page
- 10.1557/s43577‐023‐00610‐8 · DOI
- 10.1039/D4DD00013G · DOI · Paper page
- 10.1126/sciadv.adl4000 · DOI · Paper page
- 10.1002/adma.202413523 · DOI · Paper page
- A.Roberts J.Engel C.Raffel C.Hawthorne andD.Eck “AHierarchical Latent Vector Model for Learning Long‐Term Structure in Music ” inProceedings of the 35th International Conference on Machine Learning eds.J.DyandA.Krause(PML 2018) 4364–4373.
- 10.1007/s00521‐018‐3813‐6 · DOI · Paper page
- 10.1007/s00521‐018‐3758‐9 · DOI · Paper page
- Huang C.‐Z. A., 2020, MuseNet
- C.Donahue H. H.Mao Y. E.Li et al. LakhNES: Improving Multi‐Instrumental Music Generation with Cross‐Domain Pre‐Training ” inProceedings of the 20th International Society for Music Information Retrieval Conference eds.A.Flexer G.Peeters J.Urbano andA.Volk(ISMIR 2019).
- D.EckandJ.Schmidhuber “Finding Temporal Structure in Music: Blues Improvisation with LSTM Recurrent Networks ” inProceedings of the 2002 12th IEEE Workshop on Advances in neural information processing systems(IEEE 2002) vol.12.747–754 · DOI · Paper page
- 10.1016/j.eswa.2022.118190 · DOI · Paper page
- Briot J.‐P., 2017, Deep Learning Techniques for Music Generation–a Survey
- S.Ji J.Luo andX.Yang “A Comprehensive Survey on Deep Music Generation: Multi‐Level Representations Algorithms Evaluations and Future Directions ” arXiv preprint arXiv:2011.06801 2011. · arXiv
- Sawyer R. K., 2003, Group Creativity: Music, Theater, Collaboration
- 10.1016/B978-0-12-375038-9.00120-5 · doi:10.1016/b978-0-12-375038-9.00120-5
- J.SmithandJ.Doe “Swarm Intelligence for Generative Music ” inProceedings of the International Conference on Generative Art(IEEE 2020) 123–132.
- Lee E., 2018, Generating Music From Flocking Dynamics, Journal of Artificial Life and Creative Computation, 15, 245
- E. J.Hu et al. “LoRA: Low‐Rank Adaptation of Large Language Models “2021 https://arxiv.org/abs/2106.09685v2. · arXiv
- 10.1038/s44387‐025‐00003‐z · DOI
- OpenAI A.Jaech A.Kalai et al. “OpenAI o1 System Card “2024 https://arxiv.org/abs/2412.16720. · arXiv
- Minsky M., 1986, The Society of Mind
- Shortliffe E. H., 1976, Computer‐Based Medical Consultations: MYCIN
- T. B.Brown B.Mann N.Ryder et al. “Language models are few‐shot learners ” inProceedings of the 34th International Conference on Neural Information Processing Systems (NIPS ’20)(Curran Associates Inc 2020 vol.33 1877–1901 https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a‐Paper.pdf.
- 10.1038/s41586-023-05881-4 · DOI · Paper page
- 10.1007/BF01700692 · DOI · Paper page
- 10.1162/014892601300126106 · doi:10.1162/014892601300126106
- Schuijer M., 2008, Analyzing Atonal Music : Pitch‐Class Set Theory and Its Contexts
- Tymoczko D., 2011, A Geometry of Music : Harmony and Counterpoint in the Extended Common Practice
- 10.1088/2399-1984/abcf1b · DOI
- 10.1021/acsnano.9b02180 · DOI · Paper page
- 10.1088/1748-3190/ac338a · DOI
- 10.1016/J.PATTER.2023.100692 · DOI
- 10.1007/s12668‐011‐0022‐5 · DOI
- 10.1371/journal.pone.0023911 · DOI
- 10.1090/S0002-9947-1945-0013131-6 · DOI · Paper page
- Marquis J.‐P., 2019, Stanford Encyclopedia of Philosophy
- 10.1371/journal.pone.0172395 · DOI · Paper page
- K.Cao A.Lazaridou M.Lanctot andJ. Z.Leibo K.Tuyls andS.Clark “Emergent communication through negotiation ” inInternational Conference on Learning Representations(OpenReview.net 2018).
- P.Sunehag G.Lever A.Gruslys et al. “Value‐Decomposition Networks For Cooperative Multi‐Agent Learning Based On Team Reward ” inProceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS ’18)(International Foundation for Autonomous Agents and Multiagent Systems 2018) 2085–2087. · DOI · Paper page
- A.GhafarollahiandM. J.Buehler “Multi‐Agent Artificial Intelligence Model Discovers Protein Design Principles ”2025 https://arxiv.org/abs/2504.19017. · arXiv
- A.GhafarollahiandM. J.Buehler “Autonomous Inorganic Materials Discovery via Multi‐Agent Physics‐Aware Scientific Reasoning ”2025 https://arxiv.org/abs/2508.02956. · arXiv
- J.HowardandS.Ruder “Universal language model fine‐tuning for text classification ” inProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) eds.I.Gurevych andY.Miyao(Association for Computational Linguistics 2018) 328–339. · DOI · Paper page
- Weiss G., 2016, Multiagent Systems
- 10.1073/pnas.36.1.48 · DOI · Paper page
- 10.2307/1969529 · DOI · Paper page
- Kennedy J., 2001, Swarm Intelligence
- 10.1093/oso/9780195131581.001.0001 · DOI · Paper page
- M. S.CuthbertandC.Ariza ”music21: A Toolkit for Computer‐Aided Musicology and Symbolic Music Data ” inProceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR)(International Society for Music Information Retrieval 2010) 637–642.
- Lerdahl F., 2004, Tonal Pitch Space
- 10.1016/j.physa.2009.08.035 · doi:10.1016/j.physa.2009.08.035
- 10.1007/s11042-017-5175-y · DOI
- Edelsbrunner H., 2010, Computational Topology: An Introduction
- 10.1016/j.jfa.2008.11.001 · DOI · Paper page
- 10.1007/s41468-021-00071-5 · DOI · Paper page
- Sankey M. H. P. R., 1898, The Thermal Efficiency of Steam Engines, Minutes of the Proceedings of the Institution of Civil Engineers, 134, 278
- 10.1371/journal.pone.0008694 · DOI · Paper page
- L.Zheng W.‐L.Chiang Y.Sheng et al. “Judging LLM‐as‐a‐Judge with MT‐Bench and Chatbot Arena “ arXiv preprint arXiv:2306.05685 2023. · arXiv · doi:10.52202/075280-2020 · Paper page
- G.Wang Y.Li et al. “Voyager: An Open‐Ended Embodied Agent with Large Language Models “ arXiv preprint arXiv:2305.16291 2023. · arXiv
- Fudenberg D., 1991, Game Theory
- Osborne M. J., 1994, A Course in Game Theory
- 10.1112/plms/s2-45.1.161 · DOI
- 10.2307/2964649 · DOI
- 10.1145/146585.146609 · DOI · Paper page
- 10.1007/BF01200056 · DOI · Paper page
- 10.1145/3485628 · DOI · Paper page
- 10.1145/357073.357079 · DOI · Paper page
- Gilbert S. F., 2010, Developmental Biology
- Murphy K., 2012, Janeway's Immunobiology
- 10.1166/jctn.2008.2554 · doi:10.1166/jctn.2008.2554
- 10.1007/978-94-007-1611-7 · DOI
- 10.1126/science.1193147 · DOI · Paper page
- 10.1080/14789450.2019.1697236 · DOI
- Helmholtz H., 1863, On the Sensations of Tone as a Physiological Basis for the Theory of Music
- B.McFee C.Raffel‡ D.Liang et al. “librosa: Audio and music signal analysis in Python ” inProceedings of the 14th Python in Science Conference(SciPy 2015) 18–25. · DOI · Paper page
- E.Chew “Spiral array: An Algorithm for Determining Key Boundaries ” inProceedings of the International Computer Music Conference eds.C.Anagnostopoulou M.FerrandandA.Smaill(Springer 2002) 603–606. · doi:10.1007/3-540-45722-4_4
- 10.1109/18.61115 · DOI · Paper page
- G.Peeters “A large set of audio features for sound description (similarity and classification) in the CUIDADO project ” inProceedings of the International Conference on Digital Audio Effects (DAFx)(Institut de Recherche et Coordination Acoustique/Musique (IRCAM) Technical Report 2004).
- 10.1109/TASSP.1978.1163055 · DOI · Paper page
- Jolliffe I. T., 2016, Principal Component Analysis
- 10.1038/30918 · DOI · Paper page
- 10.1103/PhysRevLett.89.208701 · DOI · Paper page
- 10.1103/PhysRevE.69.066133 · DOI · Paper page
- 10.2307/3033543 · DOI · Paper page
- 10.5486/PMD.1959.6.3-4.12 · DOI · Paper page
- 10.1137/070710111 · DOI · Paper page
- 10.1109/TAC.1974.1100705 · DOI · Paper page
- Allen M. P., 1987, Computer Simulation of Liquids, 385
- 10.1007/978-0-387-76426-9 · DOI · Paper page
- Lennard‐Jones J. E., 1924, On the Determination of Molecular Fields. II. From the Equation of State of a Gas, Proceedings of the Royal Society A, 106, 463
- 10.1103/PhysRev.34.57 · DOI · Paper page
- 10.1126/science.267.5197.476 · DOI · Paper page
- 10.1038/nature03109 · DOI · Paper page
- 10.1103/PhysRevLett.75.1226 · DOI · Paper page
Metadata
- Authors
- Buehler, M. J.
- Venue
- Advanced Intelligent Systems
- Publisher
- Wiley
- Published
- 2026-04-05
- Volume
- 8
- Issue
- 5
- ISSN
- 2640-4567
- Cited by
- 2
- References
- 9
- Language
- en
- Licence
- creativecommons.org/licenses/by/4.0/ (vor)
- doi.wiley.com/10.1002/tdm_license_1.1 (tdm)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.