用群体智能生成长篇音乐，无需模型更新，效果更优且多样。
MusicSwarm: Biologically Inspired Intelligence for Music Composition
- 多个相同模型通过局部信号协作，不更新参数，仅靠交互形成音乐结构。
- 生成音乐在质量、多样性与创意上均优于中心化系统，结构更丰富。
- 适用于写作、设计等协同创作场景，计算效率高，可跨领域迁移。
我们展示，通过去中心化的、由相同且冻结的基底模型组成的群体，仅依靠利他性、点对点的信号协调，即可生成连贯的长篇音乐作品，过程中无需任何参数更新。对比有全局评价器的集中式多智能体系统，该去中心化群体中以小节为单位的智能体感知并留下和声、节奏与结构线索，动态调整短期记忆并达成共识。通过符号、音频与图论分析，该群体在质量、多样性与结构变化性方面表现更优，并在创意指标上领先。系统动态趋向于稳定互补的角色分工；自相似网络揭示出具备高效远距离连接与专用桥接结构的小世界架构，阐明了局部创新如何整合为全局音乐形式。通过将专业化从参数更新转向交互规则、共享记忆与动态共识，MusicSwarm提供了一条计算与数据高效的长时程创造性结构生成路径，且可立即应用于协作写作、设计及科学发现等非音乐领域。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。