Beyond the Vacuum: Combinatorial Strategy Selection for Competitor-Aware Generative Engine Optimization
Information Retrieval
Summary
The authors study how to rewrite content so it appears more often in answers generated by large language models. They point out that when many people optimize their content this way, the best rewriting methods change because they compete with each other. To handle this, they created a two-step approach: first, they use a smart search method to find good rewriting strategies, then they train a language model to combine these strategies effectively. Their approach works better than previous ones on various tests and works well even on new types of data.
Authors
Vaibhav Sourirajan, Yao Zhang, Himanshu Kumar, Sahil Wadhwa, Mann Patel, Amirfarrokh Iranitalab
Abstract
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.