LAWA：延迟感知的多智能体工作流优化框架
原标题：Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
AI 摘要
达特茅斯学院研究团队提出新问题「延迟感知工作流生成」，并发布 LAWA 框架，通过基于理论保证的图编辑操作优化多智能体工作流的关键路径瓶颈，在七个基准上显著降低执行时间（makespan）同时保持任务性能。该工作针对 AI 客服、云故障排查等重复查询场景，解决现有自动工作流生成方法只优化下游性能而忽略延迟的问题。代码已开源。
正文节选
Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries Abstract Large Language Model-based Multi-Agent Systems (LLM-based MAS) have shown remarkable success in solving complex tasks by coordinating specialized agents through multi-step workflows. To overcome the high cost and specificity of manually designed workflows, recent research has shifted toward learning them automatically. However, a key limitation remains: while agent calls introduce significant