让多个智能体协作学习可复用的优化策略，提升生成引擎的准确性和可信度。
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
- 多智能体协同规划、编辑与评估，逐步提炼出可复用的优化技能。
- 在三大主流引擎上，生成内容可见性与引用准确性显著优于基线方法。
- 适合关注生成式搜索可信度与跨任务策略迁移的研究者。
生成引擎（GEs）正通过引用支持的答案取代传统排序链接，重塑信息获取方式，但现有生成引擎优化（GEO）方法各自独立优化每个实例，无法积累或迁移有效策略。本文将GEO重新定义为策略学习问题，提出MAGEO多智能体框架：协调规划、编辑与保真度感知评估构成执行层，经过验证的编辑模式被逐步提炼为可复用的、引擎特定的优化技能。为实现可控评估，引入双分支评估协议以实现内容修改的因果归因，并提出DSV-CF双维度指标，统一语义可见性与归因准确性。进一步发布MSME-GEO-Bench，一个基于真实查询的多场景、多引擎基准。在三个主流引擎上的实验表明，MAGEO在可见性与引用保真度上显著优于启发式基线，消融实验证实引擎特定偏好建模与策略复用是关键增益来源，揭示了一种可扩展的学习驱动型可信GEO范式。代码已开源。
原文摘要 · Abstract (English)
Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimize each instance in isolation, unable to accumulate or transfer effective strategies across tasks and engines. We reframe GEO as a strategy learning problem and propose MAGEO, a multi-agent framework in which coordinated planning, editing, and fidelity-aware evaluation serve as the execution layer, while validated editing patterns are progressively distilled into reusable, engine-specific optimization skills. To enable controlled assessment, we introduce a Twin Branch Evaluation Protocol for causal attribution of content edits and DSV-CF, a dual-axis metric that unifies semantic visibility with attribution accuracy. We further release MSME-GEO-Bench, a multi-scenario, multi-engine benchmark grounded in real-world queries. Experiments on three mainstream engines show that MAGEO substantially outperforms heuristic baselines in both visibility and citation fidelity, with ablations confirming that engine-specific preference modeling and strategy reuse are central to these gains, suggesting a scalable learning-driven paradigm for trustworthy GEO. Code is available at https://github.com/Wu-beining/MAGEO
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。