SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization

Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers. This shift has fundamentally reshaped how web content gains exposure online, giving rise to Search-Augmented Generative Engine Optimization (SAGEO), the practice of optimizing web documents to improve their visibility in AI-generated responses. Despite growing interest, no evaluation environment currently supports comprehensive investigation of SAGEO. Existing benchmarks lack end-to-end visibility evaluation of optimization strategies, operating on pre-determined candidate documents and abstracting away retrieval and reranking stages in SAGE. They also discard structural information (e.g., schema markup) present in real web documents, overlooking the rich signals that search systems actively leverage in practice. Motivated by these gaps, we introduce SAGEO Arena, a realistic and reproducible environment for stage-level SAGEO analysis. SAGEO Arena integrates a full generative search pipeline over a large-scale corpus of web documents with rich structural information, enabling the first empirical analysis of how optimization signals propagate from retrieval to generation. Our findings reveal that existing approaches remain largely impractical, often degrading visibility in retrieval and reranking. Leveraging structural information helps mitigate these limitations, yet effective SAGEO requires tailoring optimization to each pipeline stage. Overall, our benchmark provides a practical foundation for advancing SAGEO.