{
  "abstract": "As large language models (LLMs) are increasingly used to automate digital interactions, users can leverage LLM-generated text as cover for covert communication within seemingly benign conversations. Existing LLM steganography, however, is predominantly white-box, requiring the sender and receiver to share the cover statistics, typically through access to the model weights and prompt. Black-box schemes remove this requirement by allowing the receiver to operate solely on the generated text, but current approaches rely on fixed-length, open-loop watermarking techniques that suffer from high decoding error rates under variable-length token generation. We recast black-box LLM steganography as a sequential communication problem with causal, noiseless feedback: every generated token is observed by both parties and can guide subsequent embedding. Based on this perspective, we introduce \\textbf{B}urnashev \\textbf{A}daptive Posterior \\textbf{M}atching (BAM), a feedback-coding scheme that combines posterior matching with a decode-and-confirm phase. The design is inspired by classical information-theoretic feedback-coding principles, while its security is established through a cryptographic reduction proof. Across three open-weight language models, we demonstrate that BAM attains 0-0.1\\% empirical message error on an 8-bit payload in around 50 tokens, across 1000 trials, versus 10-17\\% for the strongest black-box baseline at comparable length. Building on the proposed steganography algorithm, we demonstrate the feasibility of an end-to-end communication protocol that achieves high communication rates across multiple conversational settings.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.24994",
  "author_total": 6,
  "authors": [
    {
      "name": "Sidong Guo"
    },
    {
      "name": "Sajani Vithana"
    },
    {
      "name": "Atefeh Gilani"
    },
    {
      "name": "Lalitha Sankar"
    },
    {
      "name": "Oliver Kosut"
    },
    {
      "name": "Flavio P. Calmon"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/12rmbf9zsz09t.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.24994",
  "fulltext_url": null,
  "id": "12rmbf9zsz09t",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.24994",
  "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.CR"
    ],
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1707|Advanced Steganography and Watermarking Techniques"
    ]
  ],
  "openalex": "W7214011577",
  "pdf_url": "https://arxiv.org/pdf/2609.24994",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/12rmbf9zsz09t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:27Z",
      "native_id": "2609.24994",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.24994"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Feedback Coding Enables Inference-Time Covert Agentic Communication",
  "title_text": "Feedback Coding Enables Inference-Time Covert Agentic Communication",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:27Z",
  "url": "https://research.draconitic.com/paper/12rmbf9zsz09t",
  "venue": "arXiv",
  "versions": []
}