多智能体辅导系统在高并发下延迟飙升，不同部署模式效果差异显著。
Latency and Cost of Multi-Agent Intelligent Tutoring at Scale
- 通过多智能体分工提升回答质量，但并发请求导致延迟叠加。
- 优先计费模式可保持全负载下响应低于4秒，而标准模式在课堂级并发时严重降级。
- 适合需要预测流量的高校机构，提供从小型研讨到全校部署的选型参考。
多智能体大模型辅导系统通过智能体专业化提升回答质量，但每个学生请求会触发多个并行API调用，其延迟受并行阶段最大值效应影响，单智能体系统不存在此问题。我们对基于Gemini 2.5 Flash和Google Vertex AI构建的四智能体系统ITAS，在三种吞吐层级（Standard PayGo、Priority PayGo、Provisioned Throughput）及十一档并发水平（最高50个并发用户）下进行测试，共生成3000余次请求，数据来自真实研究生STEM课程部署。结果表明：Priority PayGo在全负载范围内保持亚4秒响应；Standard PayGo在教室规模并发下性能显著下降；Provisioned Throughput在低并发时延迟最低，但超过约20个并发用户后容量饱和。成本分析显示，两种按令牌计费模式在最坏使用场景下，人均每学期成本仍远低于一本STEM教材。当机构能预测并集中流量时，尽管持续预留成本较高，Provisioned Throughput仍具成本竞争力。研究为从小型研讨班到全校推广的不同规模部署提供了具体的层级选择指导。
原文摘要 · Abstract (English)
Multi-agent LLM tutoring systems improve response quality through agent specialization, but each student query triggers several concurrent API calls whose latencies compound through a parallel-phase maximum effect that single-agent systems do not face. We instrument ITAS, a four-agent tutoring system built on Gemini 2.5 Flash and Google Vertex AI, across three throughput tiers (Standard PayGo, Priority PayGo, and Provisioned Throughput) and eleven concurrency levels up to 50 simultaneous users, producing over 3,000 requests drawn from a live graduate STEM deployment. Priority PayGo maintains flat sub-4-second response times across the full load range; Standard PayGo degrades substantially under classroom-scale concurrency; and Provisioned Throughput delivers the lowest latency at low concurrency but saturates its reserved capacity above approximately 20 concurrent users. Cost analysis places both pay-per-token tiers well below the price of a STEM textbook per student per semester under a worst-case usage ceiling. Provisioned Throughput, expensive under continuous provisioning, becomes cost-competitive for institutions that can predict and concentrate their traffic toward high utilization. These results provide concrete tier-selection guidance across deployment scales from a single seminar to a university-wide rollout.
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。