# Communication Heterogeneity and Collective Consensus in Neural Cellular Automata

arXiv: https://arxiv.org/abs/2606.21202 · HTML: https://mlsanity.com/paper/2606.21202/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Growing 3D Artefacts and Functional Machines with Neural Cellular Automata](https://mlsanity.com/paper/2103.08737/) (2021)
- [Learning Graph Cellular Automata](https://mlsanity.com/paper/2110.14237/) (2021)
- [Growing Isotropic Neural Cellular Automata](https://mlsanity.com/paper/2205.01681/) (2022)
- [Social learning strategies modify the effect of network structure on group performance](https://mlsanity.com/paper/1606.00753/) (2016)
- [Neural Cellular Automata for ARC-AGI](https://mlsanity.com/paper/2506.15746/) (2025)
- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [A Path to Universal Neural Cellular Automata](https://mlsanity.com/paper/2505.13058/) (2025)
- [Identity Increases Stability in Neural Cellular Automata](https://mlsanity.com/paper/2508.06389/) (2025)

## Abstract (arXiv)

Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that all agents share a single communication protocol. We ask what happens when they do not. Using a Neural Cellular Automaton in which a population of cells must solve the density classification task, agreeing on a global majority that no individual can observe, we introduce ``languages'' as sub-populations that read one another's messages through a translation with a tunable ``linguistic distance''. We find that linguistic distance slows consensus, that it produces mild divergence between groups rather than full fragmentation, and that a collective whose shared rule was trained under diverse protocols is robust to mismatch; a homogeneously trained one is not. The findings hold on both a ring and a two-dimensional grid, and admit a natural reading as Ising relaxation, in which a foreign-language region acts as a boundary defect that leaves the system in a higher-energy, partially ordered state. These patterns are qualitatively consistent with effects reported in human group studies, suggesting that distance between communication protocols is a minimal mechanism sufficient to produce them, without anything language-specific.