宽度、内存与延迟：平坦多智能体系统极限的资源核算
原标题：Width, Memory, and Delay: A Resource Accounting for the Limits of Flat Multi-Agent Systems
AI 摘要
该研究针对多智能体系统（包括LLM智能体群体）的性能极限问题，提出一个定量资源模型，以群体宽度、智能体内存和观测延迟为三种资源。研究发现，平坦同质系统的性能下限由智能体内存决定，而非架构层级；三种资源不可完全互换，并存在硬性交换边界；残余性能下限由观测延迟和环境不可预测性决定。研究通过受控测试平台验证了结论，并为实践者提供了四条设计规则。
正文节选
Computer Science > Multiagent Systems Title:Width, Memory, and Delay: A Resource Accounting for the Limits of Flat Multi-Agent Systems View PDF HTML (experimental) Abstract:A recurring question in the design of scalable multi-agent systems -- from robot swarms to collectives of large-language-model (LLM) agents -- is whether adding more agents can, on its own, overcome performance limits, or whether a qualitatively \emph{deeper} organization is required. A recent preprint argues that