Evolved Collectives Combine Complex Internal Representations with Simple Outputs
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_ | 1866916075081302016 |
|---|---|
| author | Giardini, Guilherme S. Y. Hardy II, John F. daCunha, Carlo |
| author_facet | Giardini, Guilherme S. Y. Hardy II, John F. daCunha, Carlo |
| contents | Collective intelligence emerges from local interactions among agents with limited information, yet how internal controller organization relates to emergent collective order remains unclear. Here, we study evolved swarms with shallow neural controllers under explicit sensory and actuation constraints and compare collective order with hidden-layer complexity and output nonlinearity across 3024 conditions. Under these constraints, the most ordered regimes exhibit two simultaneous and seemingly contrasting effects: hidden-layer complexity increases, while the effective output mapping becomes more linear. The diversity of recurrent collective behaviors varies nonmonotonically across the control parameters, with pattern richness shaped by parameter-specific tradeoffs rather than a single generic constraint optimum. Unevolved controls show that output linearization persists without adaptation, whereas the hidden-complexity relation depends on optimization. These two effects are respectively consistent with the law of requisite complexity and ecological rationality, suggesting that adaptive collective intelligence can arise through a partitioned controller organization in which representational complexity and action-level linearization coexist within the same system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02411 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evolved Collectives Combine Complex Internal Representations with Simple Outputs Giardini, Guilherme S. Y. Hardy II, John F. daCunha, Carlo Physics and Society Adaptation and Self-Organizing Systems Collective intelligence emerges from local interactions among agents with limited information, yet how internal controller organization relates to emergent collective order remains unclear. Here, we study evolved swarms with shallow neural controllers under explicit sensory and actuation constraints and compare collective order with hidden-layer complexity and output nonlinearity across 3024 conditions. Under these constraints, the most ordered regimes exhibit two simultaneous and seemingly contrasting effects: hidden-layer complexity increases, while the effective output mapping becomes more linear. The diversity of recurrent collective behaviors varies nonmonotonically across the control parameters, with pattern richness shaped by parameter-specific tradeoffs rather than a single generic constraint optimum. Unevolved controls show that output linearization persists without adaptation, whereas the hidden-complexity relation depends on optimization. These two effects are respectively consistent with the law of requisite complexity and ecological rationality, suggesting that adaptive collective intelligence can arise through a partitioned controller organization in which representational complexity and action-level linearization coexist within the same system. |
| title | Evolved Collectives Combine Complex Internal Representations with Simple Outputs |
| topic | Physics and Society Adaptation and Self-Organizing Systems |
| url | https://arxiv.org/abs/2606.02411 |