反馈编码实现推理时隐蔽智能体通信

Computer Science > Information Theory arXiv:2609.24994 (cs) [Submitted on 21 Sep 2026] Title:Feedback Coding Enables Inference-Time Covert Agentic Communication Authors:Sidong Guo, Sajani Vithana, Atefeh Gilani, Lalitha Sankar, Oliver Kosut, Flavio P. Calmon View a PDF of the paper titled Feedback Coding Enables Inference-Time Covert Agentic Communication, by Sidong Guo and 5 other authors View PDF HTML (experimental) 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. Subjects: Information Theory (cs.IT); Cryptography and Security (cs.CR) Cite as: arXiv:2609.24994 [cs.IT] (or arXiv:2609.24994v1 [cs.IT] for this version) https://doi.org/10.48550/arXiv.2609.24994 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Sidong Guo [view email] [v1] Mon, 21 Sep 2026 17:58:22 UTC (89 KB) Full-text links: Access Paper: View a PDF of the paper titled Feedback Coding Enables Inference-Time Covert Agentic Communication, by Sidong Guo and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.IT new | recent | 2026-09 Change to browse by: cs cs.CR math math.IT References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)