Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for isolated models, how value perturbations propagate through agent interactions remains poorly understood. We present ValueFlow, a perturbation-based evaluation framework for measuring and analyzing value drift in multi-agent systems. ValueFlow introduces a 56-value evaluation dataset derived from the Schwartz Value Survey and quantifies agents' value orientations during interaction using an LLM-as-a-judge protocol. Building on this measurement layer, ValueFlow decomposes value drift into agent-level response behavior and system-level structural effects, operationalized by two metrics: beta-susceptibility, which measures an agent's sensitivity to perturbed peer signals, and system susceptibility (SS), which captures how node-level perturbations affect final system outputs. Experiments across multiple model backbones, prompt personas, value dimensions, and network structures show that susceptibility varies widely across values and is strongly shaped by structural topology.

翻译：多智能体大语言模型（LLM）系统日益由能够观察并响应彼此输出的智能体构成。尽管价值对齐通常针对孤立模型进行评估，但价值扰动如何通过智能体交互进行传播仍鲜为人知。我们提出了ValueFlow，一种基于扰动的评估框架，用于测量和分析多智能体系统中的价值漂移。ValueFlow引入了一个源自施瓦茨价值调查的56项价值评估数据集，并采用LLM作为评判者的协议来量化智能体在交互过程中的价值取向。基于此测量层，ValueFlow将价值漂移分解为智能体层面的响应行为与系统层面的结构效应，并通过两个指标进行量化：beta-敏感度（用于衡量智能体对受扰动同伴信号的敏感性）和系统敏感度（SS）（用于捕捉节点级扰动如何影响最终系统输出）。在多种模型骨干、提示角色设定、价值维度和网络结构上的实验表明，敏感度在不同价值维度间差异显著，且受结构拓扑的强烈影响。