[
    {
        "id": "osp-21878",
        "type": "article-journal",
        "title": "Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?",
        "author": [
            {
                "family": "Xie",
                "given": "Yi"
            },
            {
                "family": "Zhou",
                "given": "Zhanke"
            },
            {
                "family": "Fan",
                "given": "Yi"
            },
            {
                "family": "Ge",
                "given": "Yong"
            },
            {
                "family": "Han",
                "given": "Bo"
            },
            {
                "family": "Liu",
                "given": "Bo"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Multi-agent LLM systems pair a sender with broad context and an executor with a limited local view. We study when a short message improves the executor's next decision, when raw context is preferable, and when a stronger sender helps. Our framework, \\emph{receiver-relative bounded coordination}, expresses message utility as receiver gain minus protocol tax. Compression beats raw context when tax savings exceed losses from omitted information and decoder mismatch. Even \\emph{Bayes-sufficient} compression can fail when a bounded executor cannot use its surface form. A three-stage decomposition separates externalization, absorption, and \\emph{action closure}, explaining how errors remain after the correct content reaches the receiver. Under a single-crossing condition, sender upgrades help above a receiver-burden threshold. Across six benchmarks, the same Qwen protocol raises ContextBench joint accuracy from $0.633$ to $0.775$ but lowers ToolSandbox from $0.889$ to $0.653$. Fixed-message replay reveals closure failures despite correct artifact recovery. These results guide an inference-time selector that improves the accuracy-cost frontier on the evaluated communication regimes."
    }
]