{
  "abstract": "Recent work on large language models and agentic systems raises a basic question that current practice leaves open: how should artificial cognition be decomposed, measured, and composed? We propose studying multi-agent systems from a fixed unit we call a cognitive cell: a small, frozen language model with bounded memory and a message interface. The methodological commitment, the fixed-cell principle, is to hold this unit constant and vary only the population size, the communication topology, the message bandwidth, and the coordination protocol, so that collective behavior becomes a measurable property of a known device rather than an artifact of per-study engineering. We characterize a single cell by a compact datasheet of measurable parameters, and we ask when replicating and connecting cells improves performance: first we measure how one cell behaves alone, then we replicate it and test when voting, communication, and topology help. Instantiating the framework with small frozen models (1.5 and 3 billion parameters), we report a first round of measurements. Adding cells helps only when their errors are not too correlated. A simple correct/incorrect voting model is a useful but conservative null: real open-ended voting can exceed it, because errors are dispersed across many wrong answers rather than concentrated on one. Popular interactive protocols, namely debate, a shared blackboard, and chain revision, do not beat a matched-cost voting baseline in our setting. Finally, a cell's ability to relay several facts, itself a datasheet quantity, predicts whether a population can solve tasks whose evidence exceeds any single cell's memory. We present these as initial measurements within a broader program on scalable artificial cognition, in which multi-agent architectures appear as the special case of cells autonomous enough to be treated as agents.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.28606",
  "author_total": 1,
  "authors": [
    {
      "name": "Silvan Ferreira"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2cem4beem7td7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.28606",
  "fulltext_url": null,
  "id": "2cem4beem7td7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.28606",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.MA"
    ],
    [
      "arxiv",
      "physics.soc-ph"
    ],
    [
      "openalex",
      "1702|Multi-Agent Systems and Negotiation"
    ]
  ],
  "openalex": "W7204868956",
  "pdf_url": "https://arxiv.org/pdf/2608.28606",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2cem4beem7td7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:41Z",
      "native_id": "2608.28606",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.28606"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.soc-ph",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Cognitive Cells: A Compositional Framework for Populations of Small Language Models",
  "title_text": "Cognitive Cells: A Compositional Framework for Populations of Small Language Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:41Z",
  "url": "https://research.draconitic.com/paper/2cem4beem7td7",
  "venue": "arXiv",
  "versions": []
}