想了解多智能体LLM之间怎么互相影响输出？这篇论文给出了可量化框架CAF，还拿DeepSeek和GPT-4o-mini做了实验，能看到图像条件会放大耦合效应。
论文提出Contagion Tensor框架，量化多智能体LLM输出分布间的耦合。基于该张量定义Coupling Amplification Factor (CAF)，形式为CAF=E[T_condition]/E[T_baseline]，提供无单位基线比较。在2x2x2块正交仿真中，图像条件超线性效应(CAF=1.40)在禁用图像扰动模块后降为亚线性(CAF=0.87)。真实API实验：DeepSeek-Chat (R=30)和GPT-4o-mini (R=15,真实视觉)在统一人格下文本通信CAF≈1.0，多样人格导致收敛(CAF=0.88)。GPT-4o-mini内对比：C3 (文本) CAF=1.02 vs. C5(真实视觉,R=30) CAF=1.72，验证仿真预测。
The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables
We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (LLM) output distributions couple across modalities, agents, and time steps. From the tensor we derive the Coupling Amplification Factor (CAF), a family of ratio-based metrics sharing the form CAF = E[T_condition] / E[T_baseline], providing unitless, baseline-referenced measurement with bootstrap confidence intervals. We instantiate CAF in four variants and evaluate the strongest in a complete 2x2x2 block-orthogonal simulation design with modality-specific ablation. The ablation reveals that an apparent image-condition super-linear effect (CAF = 1.40) collapses to sub-linear (CAF = 0.87) when the image perturbation module is disabled, a shift of -0.53 with zero effect on text conditions. We supplement with real-API experiments across two model families: DeepSeek-Chat (R=30) and GPT-4o-mini (R=15, real vision). Under uniform personas, text-only communication produces CAF approx 1.0 in both models. Diverse personas drive convergence (CAF = 0.88). A within-model comparison on GPT-4o-mini reveals: C3 (text) CAF = 1.02 vs. C5 (real vision, R=30) CAF = 1.72 [1.700, 1.733], delta = +0.70, validating the simulation's super-linear image-condition prediction. Of 11 conditions, 5 have been tested on real APIs and 6 remain unverified. Our contribution is two-layered: (1) a measurement instrument that makes output-distribution coupling quantitatively falsifiable; and (2) a transferable ablation protocol that any modular multi-agent simulator can adopt to distinguish genuine coupling from design artifacts.