cs.MANov 1, 2026

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

Authors: Xuening Wu, Yanlan Kang, Qianya Xu, Haode Yang, Shan Yu, Shenqin Yin

Organizations: Pfizer Inc. · Fudan University · Cornell University · Independent researcher

Abstract

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

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Topological Sheaves of Irreducibility: A Theoretical Framework for Multi-Agent Task Obstructions

    Oct 19, 2026Steven Motta, Davide Mambelli, Alessandro RozzaMulti-Agent Systems

  2. From Emergence to Reversibility

    Nov 6, 2026Zhengye Han, Linda Ng BoyleMulti-Agent SystemsMulti-Agent Governance

  3. Artificial collectives of specialists and generalists excel at different tasks

    Jun 18, 2026John Meluso, Laurent Hébert-Dufresne, Christoph Riedl +1Multi-Agent CoordinationMulti-Agent Collaboration