Communication Heterogeneity and Collective Consensus in Neural Cellular Automata

• URL: http://arxiv.org/abs/2606.21202v1
• Date: Fri, 19 Jun 2026 08:15:29 GMT
• Title: Communication Heterogeneity and Collective Consensus in Neural Cellular Automata
• Abstract summary: We find that linguistic distance consensus produces mild divergence between groups rather than full fragmentation.<n>We 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning [80.05116806217397]
  Large Language Model (LLM) unlearning aims to suppress target knowledge while preserving general capabilities.<n>We introduce CLLPU (Cross-Lingual and Language-Bound Protocol for LLM Unlearning), a multilingual benchmark that formulates this problem through two settings.<n>Common-goal forgetting, where target knowledge should be suppressed across all languages, and language-conditioned forgetting, where suppression should remain confined to a designated language.
  arXiv  Detail & Related papers  (2026-09-05T08:26:15Z)
• HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol [54.411053382333996]
  HyLaT is a hybrid latent-text communication protocol that transmits elaborate cognitive signals through a latent channel for efficiency.<n>We introduce a two-stage training framework combining single-agent hybrid generation learning and multi-agent interactive co-training, enabling agents to generate and interpret hybrid messages.<n>Experiments demonstrate that HyLaT reduces communication overhead significantly while maintaining competitive task performance, with strong generalization and robustness across diverse settings.
  arXiv  Detail & Related papers  (2026-05-25T04:50:15Z)
• One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging [30.967619128236777]
  We study weight-space merging for multilingual machine translation by fully fine-tuning language model.<n>Our experiments reveal that merging degrades performance, especially when target languages differ.<n>These findings suggest that multilingual fine-tuning may reshape geometry in ways that reduce compatibility with standard weight-space merging assumptions.
  arXiv  Detail & Related papers  (2026-04-03T08:45:26Z)
• GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems [55.12339141172908]
  GoAgent is a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction.<n>Experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.
  arXiv  Detail & Related papers  (2026-03-20T06:21:32Z)
• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+ [4.262015666551064]
  We introduce a framework for type-matched language distances.<n>We propose novel, structure-aware representations for each distance type.<n>We unify these signals into a robust, task-agnostic composite distance.
  arXiv  Detail & Related papers  (2025-10-22T03:59:19Z)
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models [56.61984030508691]
  We present the first mechanistic interpretability study of language confusion.<n>We show that confusion points (CPs) are central to this phenomenon.<n>We show that editing a small set of critical neurons, identified via comparative analysis with a multilingual-tuned counterpart, substantially mitigates confusion.
  arXiv  Detail & Related papers  (2025-05-22T11:29:17Z)
• Bidirectional Emergent Language in Situated Environments [4.950411915351642]
  We introduce two novel cooperative environments: Multi-Agent Pong and Collectors. optimal performance requires the emergence of a communication protocol, but moderate success can be achieved without one. We find that the emerging communication is sparse, with the agents only generating meaningful messages and acting upon incoming messages in states where they cannot succeed without coordination.
  arXiv  Detail & Related papers  (2024-08-26T21:25:44Z)
• Decentralised Emergence of Robust and Adaptive Linguistic Conventions in Populations of Autonomous Agents Grounded in Continuous Worlds [4.63732827131233]
  This paper introduces a methodology through which a population of autonomous agents can establish a linguistic convention. The convention emerges in a decentralised manner through local communicative interactions between pairs of agents. We show that the methodology enables a population to converge on a communicatively effective, coherent and human-interpretable linguistic convention.
  arXiv  Detail & Related papers  (2024-01-16T16:11:35Z)
• Learning to Ground Multi-Agent Communication with Autoencoders [43.22048280036316]
  Communication requires a common language, a lingua franca, between agents. We demonstrate a simple way to ground language in learned representations. We find that a standard representation learning algorithm is sufficient for arriving at a grounded common language.
  arXiv  Detail & Related papers  (2021-10-28T17:57:26Z)
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment [59.995385574274785]
  We show that, contrary to previous belief, negative interference also impacts low-resource languages. We present a meta-learning algorithm that obtains better cross-lingual transferability and alleviates negative interference.
  arXiv  Detail & Related papers  (2020-10-06T20:48:58Z)
• Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans [75.15855405318855]
  We studied whether a modern artificial neural network trained with "deep learning" methods mimics a central aspect of human sentence processing. Although the network was solely trained to predict the next word in a large corpus, analysis showed the emergence of specialized units that successfully handled local and long-distance syntactic agreement. We tested the model's predictions in a behavioral experiment where humans detected violations in number agreement in sentences with systematic variations in the singular/plural status of multiple nouns.
  arXiv  Detail & Related papers  (2020-06-19T12:00:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.