arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.34722cs.AI
收藏

CEPO:一种用于改进多智能体系统中提示优化的通用框架

CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems

Korea University(高丽大学);KAIST(韩国科学技术院);Google Cloud AI Research(谷歌云人工智能研究院)

Jongha Kim, Seohyun Lee, Jonathan Minho Chung, Jinsung Yoon, Hyunwoo J. Kim

AI总结:

针对现有多智能体系统提示优化方法的功能耦合问题,提出CEPO通用框架,分离协调与执行,应用于四种现有提示优化器可持续提升性能,且优化效率与性能随智能体数量扩展。

摘要:

多智能体系统(MAS)既需要有效的协调,也需要专门的任务执行。现有的提示优化方法通常将这些功能耦合在特定智能体的提示中。我们引入协调者-执行者提示优化(CEPO),这是一种用于改进多智能体系统中提示优化的通用框架。CEPO通过共享协调者提示和特定智能体的执行者提示,将系统级协调与智能体级执行分离开来,并根据它们各自的角色指导其更新。这种结构允许在所有智能体中一致地优化共享协调规则,同时保持执行指令可单独调整。CEPO提供提示结构和优化指导,而现有的提示优化器执行底层搜索。涵盖四个领域11个基准的大量实验表明,将CEPO应用于四个现有的提示优化器可持续提升其性能。消融实验和定性分析支持所提出的设计,而对文档理解多智能体系统的对照研究进一步证明了优化预算效率的提升以及性能随智能体数量增加而扩展的能力。

英文摘要:

Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-specific prompts. We introduce Coordinator-Executor Prompt Optimization (CEPO), a general framework for improving prompt optimization in MAS. CEPO separates system-level coordination from agent-level execution through a shared coordinator prompt and agent-specific executor prompts, and guides their updates according to their respective roles. This structure allows shared coordination rules to be refined consistently across agents while keeping execution instructions separately adjustable. CEPO provides the prompt structure and optimization guidance, while existing prompt optimizers perform the underlying search. Extensive experiments spanning 11 benchmarks across four domains demonstrate that applying CEPO to four existing prompt optimizers consistently improves their performance. Ablations and qualitative analyses support the proposed design, while controlled studies on a document-understanding MAS further demonstrate improved optimization budget efficiency and performance scaling with the number of agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑