Metraipolis › archive › dc_ef4cc16cc910

Renormalized Cellular Intelligence: When Does Model Reduction Preserve Collective Capability? — arXiv:2611.01441

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01441
License (as archived): CC0-1.0
Archived: 2026-11-03T10:39:34.992Z
SHA-256 of the archived text: 92e95ac41f6941bc3dcad0f748045600eb5657cd122eeac6659d0bcbf305d737
Stable URL of this page: https://metraipolis.com/documento/dc_ef4cc16cc910

How to cite

Renormalized Cellular Intelligence: When Does Model Reduction Preserve Collective Capability? — arXiv:2611.01441 — arXiv (en), https://arxiv.org/abs/2611.01441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef4cc16cc910 (Metraipolis archive dc_ef4cc16cc910, sha256 92e95ac41f6941bc3dcad0f748045600eb5657cd122eeac6659d0bcbf305d737)

BibTeX

@misc{dcef4cc16cc910,
  title = {Renormalized Cellular Intelligence: When Does Model Reduction Preserve Collective Capability? — arXiv:2611.01441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef4cc16cc910; sha256 92e95ac41f6941bc3dcad0f748045600eb5657cd122eeac6659d0bcbf305d737},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As multi-agent systems grow in size and complexity, understanding which features of their interactions support collective capability becomes increasingly difficult. Can a simpler description preserve both task performance and the measured contribution of interactions between agents? Preserving collective dynamics alone is insufficient: reduction can alter decision-relevant information or give a non-communicating baseline access to pooled observations, distorting the measured advantage of interaction. We introduce Renormalized Cellular Intelligence (RCI), a framework for specifying and auditing capability preservation across scales. RCI treats the task, interacting dynamics, matched baseline, decision interfaces, and resource budget as a joint object of reduction. It specifies dynamical closure, decision compatibility, and preservation of the intended baseline comparison, and bounds the resulting error in relative capability gain. An exact analytical construction demonstrates task-score preservation, while a counterexample shows how closed reduced dynamics can erase the measured interaction gain. Using cellular systems as models of locally interacting agents, we evaluate three reduction candidates on five frozen learned models without retraining. The final candidate reduces the evolving state from eight to five dimensions per cell (37.5%). Within-run uncertainty bounds support relative gain above a prespecified threshold for the fixed model collection, yet the candidate fails the closure and decision-preservation requirements for a complete RCI certificate. RCI provides explicit criteria for distinguishing positive interaction gains from

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.01441 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:39:34.915Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).