الملخص
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.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xie, Y., Zhou, Z., Fan, Y., Ge, Y., Han, B., & Liu, B. (2026). Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems? https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems
MLA 9
Xie, Yi, et al. "Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?" https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems.
شيكاغو (المؤلف–التاريخ)
Xie, Yi, Zhanke Zhou, Yi Fan, Yong Ge, Bo Han, and Bo Liu. 2026. "Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?" https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems.
هارفارد
Xie, Y., Zhou, Z., Fan, Y., Ge, Y., Han, B. and Liu, B. (2026) 'Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?', Available at: https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems.
فانكوفر
Xie Y, Zhou Z, Fan Y, Ge Y, Han B, Liu B. Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems? https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems
IEEE
Y. Xie, Z. Zhou, Y. Fan, Y. Ge, B. Han, and B. Liu, "Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?," https://omanscience.com/ar/articles/bayes-sufficient-compression-is-not-enough-how-does-communication-help-multi-agent-systems.