Agent2UCB: Agentic System for Generative Engine Optimization
Artificial Intelligence
Summary
The authors introduce Agent2UCB, a system that helps improve how often content is noticed and used by AI search engines. It tries out nine different ways to make the content better and learns which method works best by combining prior knowledge and new feedback. The system also checks that the content remains clear, covers important topics, and seems credible. Tests show that Agent2UCB consistently makes content more visible without hurting its quality. Users can see how the system works and compare different optimization methods.
Large Language ModelsGenerative Engine OptimizationAgentic SystemsMulti-armed BanditSEO ReadinessReadabilityContent OptimizationCredibilityFeedback-driven Learning
Authors
Sheldon Yu, Rui Wang, Tong Yu, Sungchul Kim, Doga Dogan, Junda Wu, Julian McAuley
Abstract
Large language model driven search engines such as Google AI Overviews and Perplexity have created new opportunities for Generative Engine Optimization (GEO) the practice of refining content to increase its likelihood of being cited or summarized by generative systems. We demonstrate Agent2UCB, an agentic GEO system that autonomously improves content visibility through customized, feedback-driven optimization. For each content item, the system evaluates nine GEO strategies, identifies the most effective method, and accelerates selection using a bandit-based Agent2UCB policy that integrates LLM priors with online reward signals. To monitor side effects, the system also provides a lightweight, text-only SEO readiness evaluation covering readability, topical coverage, and EEAT-style credibility. Experiments on GEO-Bench show consistent visibility gains while preserving SEO quality. The demo allows users to choose the websites of interest, observe the optimization workflow, and compare GEO/SEO outcomes across methods.