arXiv cs.AI· Jongha Kim, Seohyun Lee, Jonathan Minho Chung, Jinsung Yoon, Hyunwoo J. Kim·· 14 小时前AI 评分34
CEPO：提升多智能体系统提示词优化的通用框架
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
AI 导读
研究者提出 Coordinator-Executor Prompt Optimization（CEPO）框架，将多智能体系统的系统级协调与智能体级执行拆分为共享协调提示词和各智能体专属执行提示词，并按各自角色分别引导更新。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34722 [cs.AI] |
| (or arXiv:2610.34722v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34722 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jongha Kim [view email]
[v1]
Mon, 26 Oct 2026 02:19:53 UTC (1,164 KB)
来源：arXiv cs.AI · arxiv.org