Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910223296364544 |
|---|---|
| author | Zhang, Xinyu Dou, Zhicheng Li, Deyang Tao, Jianjun Cheng, Shuo Shi, Ruifeng Liu, Fangchao Hu, Enrui Ding, Yangkai Wang, Hongbo Ye, Qi Jin, Xuefeng Zhao, Zhangchun |
| author_facet | Zhang, Xinyu Dou, Zhicheng Li, Deyang Tao, Jianjun Cheng, Shuo Shi, Ruifeng Liu, Fangchao Hu, Enrui Ding, Yangkai Wang, Hongbo Ye, Qi Jin, Xuefeng Zhao, Zhangchun |
| contents | As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple agents collaborate has emerged as a critical bottleneck. While single-agent skills can now be distributed as portable assets, multi-agent coordination protocols remain locked within framework-internal code or static configurations, preventing them from being shared across systems or autonomously improved over time. We propose \textbf{Swarm Skills}, a portable specification that extends the Anthropic Skills standard with multi-agent semantics. Swarm Skills turns multi-agent workflows into first-class, distributable assets that consist of roles, workflows, execution bounds, and a built-in semantic structure for self-evolution. To operationalize the specification's evolving nature, we present a companion self-evolution algorithm that automatically distills successful execution trajectories into new Swarm Skills and continuously patches existing ones based on multi-dimensional scoring (Effectiveness, Utilization, and Freshness), eliminating the need for human-in-the-loop oversight during the refinement process. Through an architectural compatibility analysis and a comprehensive qualitative case study using the open-source JiuwenSwarm reference implementation, we demonstrate how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10052 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering Zhang, Xinyu Dou, Zhicheng Li, Deyang Tao, Jianjun Cheng, Shuo Shi, Ruifeng Liu, Fangchao Hu, Enrui Ding, Yangkai Wang, Hongbo Ye, Qi Jin, Xuefeng Zhao, Zhangchun Computation and Language Artificial Intelligence As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple agents collaborate has emerged as a critical bottleneck. While single-agent skills can now be distributed as portable assets, multi-agent coordination protocols remain locked within framework-internal code or static configurations, preventing them from being shared across systems or autonomously improved over time. We propose \textbf{Swarm Skills}, a portable specification that extends the Anthropic Skills standard with multi-agent semantics. Swarm Skills turns multi-agent workflows into first-class, distributable assets that consist of roles, workflows, execution bounds, and a built-in semantic structure for self-evolution. To operationalize the specification's evolving nature, we present a companion self-evolution algorithm that automatically distills successful execution trajectories into new Swarm Skills and continuously patches existing ones based on multi-dimensional scoring (Effectiveness, Utilization, and Freshness), eliminating the need for human-in-the-loop oversight during the refinement process. Through an architectural compatibility analysis and a comprehensive qualitative case study using the open-source JiuwenSwarm reference implementation, we demonstrate how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in. |
| title | Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10052 |