提出时序视角空间，可检测多智能体系统中的行为变化。
Detecting Perspective Shifts in Multi-agent Systems
- 构建时序数据核视角空间，联合嵌入跨时间的智能体
- 设计新假设检验方法，能灵敏识别个体与群体行为突变
- 适用于黑箱多智能体系统，适合监控大规模生成式智能体
具备外部工具和更新机制（即智能体）的生成模型已展现出超越基础模型智能提示的能力。随着智能体应用增多，动态多智能体系统自然涌现。现有研究聚焦于单一时点查询响应的低维表示特性。本文提出时序数据核视角空间（TDKPS），联合嵌入跨时间的智能体，并提出若干新颖的假设检验方法，用于在黑箱多智能体系统中检测个体与群体层面的行为变化。我们通过模拟演化数字人格的多智能体系统，刻画了所提检验方法的实证性质，包括对关键超参数的敏感性。最终，通过自然实验验证，这些检验方法能敏锐、具体且显著地捕捉到与真实外生事件相关的改变。据我们所知，TDKPS是首个针对黑箱多智能体系统行为动态监测的原理性框架，这在生成式智能体部署持续扩大的背景下至关重要。
原文摘要 · Abstract (English)
Generative models augmented with external tools and update mechanisms (or \textit{agents}) have demonstrated capabilities beyond intelligent prompting of base models. As agent use proliferates, dynamic multi-agent systems have naturally emerged. Recent work has investigated the theoretical and empirical properties of low-dimensional representations of agents based on query responses at a single time point. This paper introduces the Temporal Data Kernel Perspective Space (TDKPS), which jointly embeds agents across time, and proposes several novel hypothesis tests for detecting behavioral change at the agent- and group-level in black-box multi-agent systems. We characterize the empirical properties of our proposed tests, including their sensitivity to key hyperparameters, in simulations motivated by a multi-agent system of evolving digital personas. Finally, we demonstrate via natural experiment that our proposed tests detect changes that correlate sensitively, specifically, and significantly with a real exogenous event. As far as we are aware, TDKPS is the first principled framework for monitoring behavioral dynamics in black-box multi-agent systems -- a critical capability as generative agent deployment continues to scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。