CEPO:改善多智能體系統提示詞優化的通用框架
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
CEPO(Coordinator-Executor Prompt Optimization)透過分離共享協調與智能體專屬執行,改善多智能體系統的提示詞優化。涵蓋四個領域的 11 項基準測試顯示,將 CEPO 用於四種現有提示詞優化器均能提升表現;文件理解多智能體系統的受控研究亦顯示,其優化預算效率及隨智能體數量增加的表現均有改善。
Published on Oct 26
Authors:
,
,
,
Abstract
CEPO improves multi-agent prompt optimization by separating shared coordination from agent-specific execution, boosting performance across benchmarks and scaling efficiently with more agents.
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.
View arXiv page View PDF Project page GitHub 8 Add to collection
Get this paper in your agent:
hf papers read 2610.34722
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.34722 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.34722 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.34722 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co