MoFlow：多目标智能体工作流生成
原标题：MoFlow: Multi-Objective Agentic Workflow Generation
AI 摘要
研究者提出 MoFlow，一种多目标智能体工作流生成方法，将工作流生成建模为多目标马尔可夫决策过程，并用凸包蒙特卡洛树搜索与乐观集合值回传求解，使单次搜索即可近似覆盖帕累托前沿，无需针对不同偏好重新训练。在数学、代码和问答六个基准、五个目标（准确率、一致性、鲁棒性、成本、延迟）上，MoFlow 两个变体在四个基准取得最高超体积，另两个基准落后最佳不到 1%，平均排名第一和第二。代码已开源。
正文节选
MoFlow: Multi-Objective Agentic Workflow Generation Abstract We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Existing methods for workflow generation typically optimize accuracy alone or a weighted sum of objectives, so each trained generator commits to one fixed trade-off and must be retrained from scratch when preferences change. To alleviate this, we propose MoFlow, which generates workflows