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

Hugging Face Daily Papers Papers
multi-agent-systems prompt-optimization prompt-engineering coordinator-executor benchmark-evaluation agent-framework

Summary

CEPO is a general framework for prompt optimization in multi-agent systems that separates shared system-level coordination from agent-specific execution prompts, consistently improving four existing prompt optimizers across 11 benchmarks in four domains.

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.
Original Article
View Cached Full Text

Cached at: 11/02/26, 07:29 AM

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

Source: https://huggingface.co/papers/2610.34722

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. Existingprompt optimizationapproaches typically couple these functions within agent-specific prompts. We introduceCoordinator-Executor Prompt Optimization(CEPO), a general framework for improvingprompt optimizationin MAS.CEPOseparates system-level coordination from agent-level execution through a sharedcoordinator promptand agent-specificexecutor 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.CEPOprovides the prompt structure and optimization guidance, while existing prompt optimizers perform the underlying search. Extensive experiments spanning 11 benchmarks across four domains demonstrate that applyingCEPOto 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 pageView PDFProject pageGitHub8Add 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 paper0

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 paper0

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 paper0

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 paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

arXiv cs.CL

SePO (Self-Evolving Prompt Optimization) proposes a self-referential prompt agent that optimizes both task agents' system prompts and its own system prompt through an evolutionary search, outperforming Manual-CoT, TextGrad, and MetaSPO across five benchmarks including AIME'25, ARC-AGI-1, and GPQA.

From Monolithic to Modular: Segment-level Automatic Prompt Optimization

arXiv cs.AI

This paper introduces SAPO, a segment-level automatic prompt optimization method that decomposes prompts into role, context, tasks, and output format, then applies targeted improvements based on weak and strong examples. Evaluated across several benchmarks, SAPO outperforms strong APO baselines including APE, OPRO, EvoPrompt, GEPA, and StraGO on GPT-3.5-Turbo and GPT-4o-mini.

MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization

arXiv cs.CL

This paper introduces MAGE, a framework for analyzing component interactions in prompt optimization, revealing a Prompt Optimization Coupling Effect (POCE) where combining multiple stochastic signals improves performance but increases variance. It provides insights into stability-performance trade-offs and practical guidance for prompt optimization.

Environment-Grounded Automated Prompt Optimization for LLM Game Agents

arXiv cs.CL

Introduces an automated prompt optimization framework for LLM game agents that decomposes the observation-to-action pipeline into two agents and iteratively refines prompts via an evolutionary loop guided by environment returns. Evaluated on BabyAI tasks, it significantly improves success rates (e.g., from 0% to 72.5% on PutNext) without updating model weights.