发表机构
Agent Network Research; The Chinese University of Hong Kong; The Hong Kong University of Science and Technology; University of Science and Technology of China（代理网络研究; 香港中文大学; 香港科学与技术大学; 中国科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人工智能智能体网络连接价值，通过建模推导最优协作协议属性，引入ANet Patu-1协议。结果表明，异构便宜模型集体价值能超同构强模型，且异构网络能自收敛重构连接价值规律。
AI 中文摘要
互联网让我们知道网络的价值取决于其节点的连接方式：广播星型网络规模为\(V\propto N\)（萨尔诺夫），全连接网格网络为\(N^2\)（梅特卡夫），群组形成网络为\(2^{N}\)（里德）。我们针对人工智能智能体网络提出类似问题。将连接的净值建模为协调组规模的函数，从中推导出最优协作协议必须具备的属性，并引入ANet Patu-1——一种自组织共识协议，网络能持续重新形成自身联盟，在\(O(1)\)并行共识轮次下自适应地处于所有三种模式的上限。为在无观点评分的情况下衡量价值，通过正式指定并推导其复杂度来对一个涌现协议进行评分，就像分析分布式算法那样。有两个结果：一是涌现性，一群最便宜的异构模型开始较弱但其集体价值随\(N\)增长并超过一群更强的同构模型；二是自反性，一个异构网络仅根据自身问题且无设计提示就能收敛到ANet Patu-1本身，重构支配其自身连接价值的高维规律。
英文摘要
The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as $V\!\propto\!N$ (Sarnoff), fully-connected meshes as $N^2$ (Metcalfe), and group-forming networks as $2^{N}$ (Reed). We ask the analogous question for networks of AI agents. We model the net value of connection as a function of coordination-group size, derive from it the properties an optimal collaboration protocol must have, and introduce ANet Patu-1 -- a self-organizing consensus protocol in which the network continuously re-forms its own coalitions, adaptively riding the upper envelope of all three regimes at $O(1)$ parallel consensus rounds. To measure value without opinion-grading, we score an emergent protocol by formally specifying it and deriving its complexity, the way distributed algorithms are analyzed. Two results follow. (i)~Emergence -- a crowd of the \emph{cheapest} model, when heterogeneous, starts weak but its collective value compounds with $N$ and \emph{overtakes} a crowd of a far \emph{stronger} model that is homogeneous: a crossover that marks a scaling law for collaboration rather than for scale. (ii)~Reflexivity -- a heterogeneous network, given only its own problem and no design hints, converges on ANet Patu-1 itself, reconstructing the high-dimensional law that governs its own connective value.
