SWORD：面向用户行为模拟的工作流与提示联合优化
原标题：Joint Workflow and Prompt Optimization for User Behavior Simulation
AI 摘要
研究者提出 SWORD 框架，用于用户行为模拟，可联合优化多智能体工作流拓扑与自然语言提示，仅依赖标量任务指标（MAE/RMSE）驱动，无需领域专家初始化或任务特定工程。实验显示其在受控同骨干对比下显著优于仅提示优化、仅工作流优化和分阶段优化基线，并在使用更小骨干模型、更少训练数据和每数据集 4-6 美元 API 成本的情况下，超过最强的已发表领域专用基线。SWORD 还能仅从标量误差反馈中自主发现领域相关信号，如评论情感映射规则和流行病学衰减先验。
正文节选
Joint Workflow and Prompt Optimization for User Behavior Simulation Abstract. User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supports system testing and evaluation, decision-making and forecasting, and user experience design. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. SWORD (Simulation-driven Workflow and Prompt Optimiz