MA-SAPO：面向分数感知提示优化的多智能体推理框架

Computer Science > Multiagent Systems arXiv:2510.16635 (cs) [Submitted on 18 Oct 2025 (v1), last revised 27 Sep 2026 (this version, v3)] Title:MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization Authors:Juhyeon Lee, Wonduk Seo, Junseo Koh, Wonseok Choi, Hyunjin An, Jian Park, Seunghyun lee, Haihua Chen, Yi Bu View a PDF of the paper titled MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization, by Juhyeon Lee and 8 other authors View PDF HTML (experimental) Abstract:Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without explaining why prompts succeed or fail. Moreover, they involve repetitive trial-and-error refinements that remain implicit, offering limited interpretability or actionable guidance for systematic improvement. In this paper, we propose MA-SAPO: a new Multi-Agent Reasoning for Score Aware Prompt Optimization framework that links evaluation outcomes directly to targeted refinements. Specifically, in the Training Phase, multiple agents interpret evaluation scores, diagnose weaknesses, and generate concrete revision directives, which are stored as reusable reasoning assets. In the Test Phase, an analyzer agent retrieves relevant exemplars and assets for a new prompt, and a refiner agent applies evidence-based edits to improve the prompt and its response. By grounding optimization in structured reasoning, MA-SAPO ensures edits are interpretable, auditable, and controllable. Experiments on the HelpSteer1/2 benchmarks show that our framework consistently outperforms single-pass prompting, retrieval-augmented generation, and prior multi-agent methods across multiple evaluation metrics. Comments: Subjects: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Information Retrieval (cs.IR) Cite as: arXiv:2510.16635 [cs.MA] (or arXiv:2510.16635v3 [cs.MA] for this version) https://doi.org/10.48550/arXiv.2510.16635 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Wonduk Seo [view email] [v1] Sat, 18 Oct 2025 20:21:09 UTC (1,304 KB) [v2] Mon, 30 Mar 2026 21:53:02 UTC (3,435 KB) [v3] Sun, 27 Sep 2026 20:17:01 UTC (3,443 KB) Full-text links: Access Paper: View a PDF of the paper titled MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization, by Juhyeon Lee and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.MA new | recent | 2025-10 Change to browse by: cs cs.AI cs.CL cs.HC cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both 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. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)