EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents

TL;DR

EcoGEO introduces a trajectory-aware ecosystem approach to optimize web-enabled LLM agents by shaping their evidence environment, leading to improved product recommendation performance over page-level methods.

Contribution

We propose EcoGEO and TRACE, a novel ecosystem-level framework and method for influencing web-enabled LLM agents across browsing trajectories, beyond individual page optimization.

Findings

EcoGEO outperforms page-level GEO baselines in product recommendation accuracy.

Trajectory-aware metrics indicate better evidence acquisition and search behavior.

Shaping the evidence environment influences the agent's search process more than content volume.

Abstract

Web-enabled LLM agents are changing how online information influences search outcomes. \ Existing Generative Engine Optimization (GEO) studies mainly focus on individual webpages. \ However, agentic web search is not a single-document setting: an agent may issue queries, crawl pages, follow links, reformulate searches, and synthesize evidence across multiple browsing steps. \ Influence therefore depends not only on page content, but also on how pages are organized, connected, and encountered along the agent's browsing trajectory. \ We study this shift through \textbf{Ecosystem Generative Engine Optimization} (\textbf{EcoGEO}), which treats GEO as an environment-level influence problem for web-enabled LLM agents. \ To instantiate this perspective, we propose \textbf{TRACE}, a \textbf{Trajectory-Aware Coordinated Evidence Ecosystem}. \ Given a recommendation query and a fictional target product, our method builds a controlled evidence environment that coordinates an agent-facing navigation entry page with heterogeneous support pages. \ These pages use shared terminology, internal links, and consistent product attributes to introduce, verify, and reinforce the target product. We evaluate our method on OPR-Bench, a benchmark for open-ended product recommendation. \ Experiments show that it consistently outperforms page-level GEO baselines in final target recommendation. \ Trajectory-level metrics further show increased initial target-result crawls, target-specific follow-up searches, and internal-link crawls, suggesting that the gains come from shaping the agent's evidence-acquisition process rather than merely adding more target-related content. \ Overall, our findings support an ecosystem research paradigm for GEO, where web-enabled LLM agents are studied in relation to the broader evidence environments that guide search, browsing, and answer synthesis.