AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
Jiaqi Yuan School of Computer Science and Engineering, Beihang UniversityBeijingChina , Jialu Wang Independent ContributorCA, United States , Zihan Wang School of Computer Science and Engineering, Beihang UniversityBeijingChina , Qingyun Sun School of Computer Science and Engineering, Beihang UniversityBeijingChina , Ruijie Wang School of Computer Science and Engineering, Beihang UniversityBeijingChina and Jianxin Li School of Computer Science and Engineering, Beihang UniversityBeijingChina
Abstract
Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization (GEO), specifically, aims to maximize visibility and attribution in black-box summarized outputs by strategically manipulating source content. However, existing methods rely on static heuristics, single-prompt optimization, or engine preference rule distillation that is prone to overfitting. They cannot flexibly adapt to diverse content or the changing behaviors of generative engines. Moreover, effectively optimizing these strategies requires an impractical amount of interaction feedback from the engines. To address these challenges, we propose AgenticGEO, a self-evolving agentic framework formulating optimization as a content-conditioned control problem, which enhances intrinsic content quality to robustly adapt to the unpredictable behaviors of black-box engines. Unlike fixed-strategy methods, AgenticGEO employs a MAP-Elites archive to evolve diverse, compositional strategies. To mitigate interaction costs, we introduce a Co-Evolving
中文速览
生成式搜索把传统“争排名”变成了让内容被大模型答案采纳并引用，但现有生成式引擎优化（GEO）方法依赖固定套路、容易过拟合，而且需要大量昂贵的引擎反馈。AgenticGEO将问题视为根据内容特点选择策略的动态控制任务，用MAP-Elites维护一个不断进化且多样化的改写策略库，并训练一个协同进化的轻量评估器来模拟黑箱搜索引擎反馈、挑选策略和规划多轮改写。实验显示，它在两个代表性生成式引擎和三个数据集上击败14种基线，平均提升46.4%，在仅使用41.2%反馈的情况下仍保留98.1%的效果，并能迁移到新领域。其重要性在于，它让内容优化不再依赖一套僵化规则，而是能以较低交互成本适应不同内容和不断变化的搜索引擎。
原文 arXiv:2603.20213;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2603.20213v1