一篇新论文详细介绍了大规模多智能体智能辅导系统的延迟和成本，该系统使用了一个名为ITAS的四智能体系统，该系统构建在Gemini 2.5 Flash和Google Vertex AI之上。研究分析了不同吞吐量级别和并发级别下的性能，发现Priority PayGo提供了持续的4秒以下响应时间。成本分析表明，按token付费的级别比传统教科书便宜得多，而预留吞吐量对于可预测的流量来说具有成本效益。 AI
影响 为教育系统选择基于延迟和成本的AI部署级别提供了具体指导。
排序理由 学术论文，详细分析了AI辅导系统的性能和成本。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.24110v1 Announce Type: cross Abstract: 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-agen…
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-…