{"slug": "cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems", "title": "CEPO: General Framework for Improving Prompt Optimization in Multi-Agent Systems", "summary": "A paper submitted to arXiv on 26 October 2026 introduces Coordinator-Executor Prompt Optimization (CEPO), a framework that separates system-level coordination from agent-level execution in multi-agent systems through a shared coordinator prompt and agent-specific executor prompts. The authors report that applying CEPO to four existing prompt optimizers consistently improved their performance across 11 benchmarks spanning four domains, with ablations and a controlled document-understanding multi-agent study showing better optimization budget efficiency and performance scaling with the number of agents. CEPO supplies only the prompt structure and optimization guidance, leaving the underlying search to existing optimizers.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 26 Oct 2026]\n\n# Title:CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems\n\n[View PDF](https://arxiv.org/pdf/2610.34722)\n\n[HTML (experimental)](https://arxiv.org/html/2610.34722v1)\n\nAbstract: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.\n    \n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems", "canonical_source": "https://arxiv.org/abs/2610.34722", "published_at": "2026-11-02 04:58:54+00:00", "updated_at": "2026-11-02 05:23:08.285690+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-agents", "large-language-models"], "entities": ["arXiv", "CEPO", "Coordinator-Executor Prompt Optimization"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems", "markdown": "https://wpnews.pro/news/cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems.md", "text": "https://wpnews.pro/news/cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems.txt", "jsonld": "https://wpnews.pro/news/cepo-general-framework-for-improving-prompt-optimization-in-multi-agent-systems.jsonld"}}