发表机构
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究临床多智能体语言模型网络中语义漂移的谱动力学，通过映射多智能体通信不确定性轨迹到嵌入空间，揭示结构瓶颈危害。提出动态谱监测技术，经图拉普拉斯算子特征分解确保全局状态扩散，保障自主医疗诊断可靠性。
AI 中文摘要
在多智能体诊断框架中集成迭代语言模型需要对底层通信拓扑进行严格的定量重新评估。常用的架构范式依赖于无标度或小世界网络，假定通信效率最优。本研究从数学上拆解了语义数据的这一假设。通过使用巴拉巴西－阿尔伯特（BA）和瓦茨－斯托加茨（WS）网络，经由解析各向同性方差代理将多智能体通信不确定性轨迹映射到768维的生物临床BERT嵌入空间，证明结构瓶颈会损害诊断安全性。相变矩阵表明局部密集团块限制了幻觉数据，导致系统趋向永久熵饱和阈值\(H_{\infty} \approx 5.947\)。结果测量到严重的终端余弦相似度下降53.29%，完全覆盖了原始真实情况。此外，终端语义漂移显示在高度聚类架构中灾难性方差放大51.81%（\(\rho = 1.5181\)），与厄多斯－雷尼配置（\(\rho = 1.0766\)）相比证明系统完全不可预测。以中心节点为中心的系统非但没有减少错误，反而自主加剧局部幻觉。通过引入时间复杂度为\(\mathcal{O}(N^3)\)的动态谱监测，并通过图拉普拉斯算子的连续特征分解对代数连通性（\(\lambda_{2_{min}}\)）施加严格下限，提出一种数学上严格的技术来确保全局状态扩散。确保自主医疗诊断的可靠性需要将拓扑稳定性视为不可协商的定量要求。
英文摘要
The integration of iterative LLMs within multi-agent diagnostic frameworks requires a rigorous quantitative reevaluation of underlying communication topologies. Frequently used architectural paradigms depend on scale-free or small-world networks, assuming optimal communication efficiency. Our study mathematically dismantles that assumption for semantic data. By mapping multi-agent communication uncertainty trajectories onto a 768-dimensional Bio_ClinicalBERT embedding space via an analytical isotropic variance proxy using Barab'asi--Albert (BA) and Watts--Strogatz (WS) networks, we prove that structural bottlenecks compromise diagnostic safety. Our phase transition matrices illustrate that localized dense cliques confine hallucinated data, preventing global consensus and forcing the system toward a permanent entropy saturation threshold of $H_{\infty} \approx 5.947$. As a result, we measure a severe terminal cosine similarity degradation of 53.29%, completely overwriting the original ground-truth. Moreover, the terminal semantic drift reveals a catastrophic variance amplification of 51.81% ($ρ= 1.5181$) in highly clustered architectures, proving total system unpredictability when compared to Erdős--R'enyi configurations ($ρ= 1.0766$). Instead of reducing errors, hub-centric systems autonomously compound localized hallucinations. By introducing dynamic spectral monitoring operating at an $\mathcal{O}(N^3)$ time complexity and imposing a strict lower bound on algebraic connectivity ($λ_{2_{min}}$) via the continuous eigen-decomposition of the graph Laplacian, we present a mathematically rigorous technique to ensure global state diffusion. Securing the reliability of autonomous medical diagnostics necessitates treating topological stability as a non-negotiable quantitative imperative.
