挖掘多智能体工作流的设计空间
原标题：Mining the Design Space of Multi-Agent Workflows
AI 摘要
该论文提出一个两阶段流程，从多智能体工作流搜索轨迹中挖掘可复现的设计原则。作者复用 AFlow 的 MCTS 优化器，在 26 个 Enigmata 推理任务上生成 28,568 个可执行工作流，再用 AutoResearch 循环在留出搜索上验证候选原则。结果显示：以 Star 扇出为入口的工作流表现更差，SharedMemory 优于 Debate，提示词具体性和占位符上下文路由带来的增益可与通信结构选择相当。
正文节选
Mining the Design Space of Multi-Agent Workflows Abstract Designing large language model (LLM) multi-agent systems (MAS) still relies on trial and error and informal “folk wisdom.” Manual studies test only a few communication structures or topologies (e.g., sequential, parallel, shared-memory, or debate), while automated optimizers discard search trajectories after selecting a task-specific workflow. We present a two-phase pipeline for mining reproducible design principles from workflow code and