研究智能体系统通信拓扑如何影响大模型调用的流量模式。
Towards Traffic Modelling of Multi-Agent Systems: The Role of Coordination Topology
- 通过实测不同拓扑结构下的调用间隔分布，分析协调逻辑对流量的影响。
- 发现星型拓扑引入了双峰分布，推理阶段服从对数正态分布。
- 适合关注多智能体系统性能与网络设计的研究者参考。
多智能体大模型系统是一种新兴的网络化工作负载，其快速部署引发了对其生成流量模式的疑问。与传统应用不同，这类系统内部产生请求：单个用户任务会引发由协调逻辑决定时序的结构化模型调用序列。现有针对人类驱动工作负载的经典流量模型是否适用尚不明确。本文通过在500次重复运行中，使用多层测量框架，对串行、星型和全连接三种智能体协调拓扑下的LLM调用间隔分布进行了实证分析。结果表明，拓扑结构从根本上塑造了对LLM后端的请求到达过程：扇出式协调引入了串行执行中不存在的结构性双峰分布；推理阶段最符合对数正态分布，而泊松指数零模型在所有拓扑中均被显著拒绝。这些差异进一步影响推断与网络层面指标。分析框架与代码已开源于https://github.com/dlamagna/agentraffic。
原文摘要 · Abstract (English)
Multi-agent LLM systems are an emerging networked workload whose rapid deployment raises questions about the traffic patterns they generate. Compared to conventional applications, these systems generate requests internally: a single user task can induce a structured sequence of model calls whose timing is governed by coordination logic rather than by user arrival rate. It is not clear whether classical traffic models, designed for human-driven workloads, apply to this setting. We present an empirical characterisation of LLM-call interarrival time distributions across sequential, star, and full-mesh agentic coordination topologies, using a multi-layer measurement framework over 500 repeated runs per topology. We find that topology fundamentally shapes the arrival process of requests to the LLM backend: fan-out coordination introduces a structural bimodality absent in sequential execution, and the reasoningphase component is best described by a log-normal distribution, with the Poisson exponential null model decisively rejected across all topologies. These differences propagate to inference and network level metrics. The framework and analysis pipeline are released openly at https://github.com/dlamagna/agentraffic.
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。