AI 中文总结
本研究将生成式引擎优化（GEO）形式化为感知竞争对手的策略选择问题，提出两阶段流程，在相关基准及合成数据集上实现最优性能且可跨域迁移。
AI 中文摘要
生成式引擎优化（GEO）已成为一种新型范式，用于转化内容以提升其在大型语言模型（LLM）响应中的可见性。然而，传统GEO方法孤立地选择改写策略，忽视了一个关键外部因素：随着内容优化应用的普及，改写内容的最优策略会发生变化。我们将GEO形式化为感知竞争对手的策略选择问题，并提出一种两阶段流程来解决该问题：（1）使用组合结构的贝叶斯优化（BOCS）高效搜索改写策略的空间；（2）从BOCS的黑箱观测中生成偏好对和基于事实的推理轨迹，以微调语言模型，使其能分析文档语料库并提出最优改写策略组合。在geo-bench基准及我们合成增强的竞争数据集geo-bench_comp上，我们的方法在多个曝光指标上均超越了现有智能体方法和单启发式方法，达到了当前最优性能。此外，该方法可迁移至多个分布外数据集，证明其在不同领域、查询和文档类型中均有效。
英文摘要
Generative Engine Optimization (GEO) has emerged as a novel paradigm for transforming content to increase visibility in Large Language Model (LLM) responses. Traditional GEO methods, however, select rewriting strategies in isolation, ignoring a critical externality: as adoption of content optimization grows, optimal strategies for rewriting content change. We formalize GEO as a competitor-aware strategy selection problem and propose a two-phase pipeline to solve it: (1) We use Bayesian Optimization of Combinatorial Structures (BOCS) to efficiently search the space of rewriting strategies, (2) We generate preference pairs and grounded reasoning traces from the BOCS black-box observations to fine-tune a language model to analyze a document corpus and propose optimal rewriting strategy combinations. We achieve state-of-the-art performance across several impression metrics over existing agentic and single-heuristic methods on both geo-bench and our synthetically augmented competitive dataset geo-bench_comp. Our method also transfers to multiple out-of-distribution datasets, proving effective across domains, queries, and document types.
Comments20 pages, 2 figures
