{
  "abstract": "Distributed intelligence concerns systems in which semi-autonomous components with local dynamics and partial observations coordinate through information exchange to maintain a shared function. This paper proposes an operational way to study such systems: measure information at the interface where a message changes a receiving action, then connect that measure to function by intervention and disturbance evaluation. We instantiate this proposal in DI-Walker, a two-dimensional four-limb embodied plant controlled by frozen Cross-Entropy-Method policies. We compare a controller using each limb's own realized-force sensor with one using the realized-force sensors of peer limbs. Under limb loss, limb slip, and weak central-control dropout, Peer-Sensor has lower late tracking error in several conditions. A corrected finite-history action-predictive estimator shows a substantially larger peer-message gain under compound failure. A future scalar functional-prediction estimator does not show the same stable advantage. We interpret this discrepancy as a methodological result: information useful for an intermediate control action can be hidden by later plant dynamics, redundancy, and context. The paper relates this result to Predictive Information, Transfer Entropy, Directed Information, information-to-go/IT-PAC ideas, empowerment, and the robust control data-rate perspective, while explicitly distinguishing operational predictive gains from exact Directed Information, channel capacity, and a formal data-rate theorem.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.27580",
  "author_total": 1,
  "authors": [
    {
      "name": "Shlomo Dubnov"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7drf7abwdkr2h.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.27580",
  "fulltext_url": null,
  "id": "7drf7abwdkr2h",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.27580",
  "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.IT"
    ],
    [
      "arxiv",
      "cs.RO"
    ],
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.IT"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.27580",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7drf7abwdkr2h.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:00Z",
      "native_id": "2609.27580",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.27580"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Action-Directed Information for Distributed Control and Agentic Interaction",
  "title_text": "Action-Directed Information for Distributed Control and Agentic Interaction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:00Z",
  "url": "https://research.draconitic.com/paper/7drf7abwdkr2h",
  "venue": "arXiv",
  "versions": []
}