将多智能体提示优化建模为最大后验推断，提升协作效率
MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference
- 把多智能体提示优化转化为最大后验推断问题，用语言引导的信念传播求解
- 在多个任务基准上超越人工设计与现有自动方法，实现性能领先
- 通过反馈驱动的拓扑感知更新机制，解决责任归属难题，适合构建可靠多智能体系统
大型语言模型（LLMs）在多样化任务中展现出卓越能力，基于LLM的智能体进一步拓展了其在实际工作流中的应用。尽管多智能体系统（MAS）通过角色分工可超越单智能体表现，但提示敏感性和系统级不稳定性使得设计困难。现有自动化提示设计虽减少人工成本，但多智能体提示优化仍缺乏系统性方法。搜索空间指数膨胀与责任分配模糊导致设计难以进行。为此，本文提出多智能体提示优化（MAPRO），一个四阶段框架：首先将多智能体提示优化建模为最大后验（MAP）推断问题，并采用语言引导的最大乘积信念传播算法求解；为解决责任分配并迭代更新系统，引入拓扑感知精炼机制，融合执行反馈与下游归因信息，选择性更新各智能体提示。该过程逐步收敛至一组协调的智能体专用提示策略。在多种任务的基准测试中，MAPRO持续优于人工设计基线与近期自动化方案，达到当前最优性能。此外，基于MAP的建模也为未来构建更可靠、有原则的多智能体系统提供通用指导。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. While recent progress shows that multi-agent systems (MAS) can outperform single agents by coordinating specialized roles, designing effective MAS remains difficult due to prompt sensitivity and the compounded instability MAS creates. To cope with the challenge, recent efforts in automated prompt design have reduced manual effort. However, multi-agent prompt optimization remains largely unexplored. Challenges like exponentially expanding search space and ambiguous credit assignment together make systematic design intractable without principled methods. Therefore, we introduce M}ulti-Agent PRompt Optimization (MAPRO), a four-stage framework that first formulates MAS prompt optimization as a Maximum a Posteriori (MAP) inference problem and solves it using a language-guided variant of max-product belief propagation algorithm. To address credit assignment and updates the system iteratively, MAPRO employs a topology-aware refinement mechanism that integrates execution feedback and downstream blames to selectively update agent prompts. Through this process, MAPRO progressively converges to a coordinated set of agent-specific prompt policies. Across benchmarks in various tasks, MAPRO achieves state-of-the-art performance, consistently surpassing manually engineered baselines and recent automated alternatives. Beyond performance, our MAP-based formulation also delivers general guidelines for building more reliable and principled multi-agent systems in the future
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。