From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning

TL;DR

This paper introduces MAGEO, a multi-agent framework for strategy learning in Generative Engine Optimization, enabling transfer of effective strategies across tasks and engines to improve citation fidelity and visibility.

Contribution

It reframes GEO as a strategy learning problem, proposing a multi-agent approach with reusable, engine-specific optimization skills and a new benchmark for evaluation.

Findings

MAGEO outperforms heuristic baselines in visibility and citation fidelity.

Engine-specific preference modeling and strategy reuse are key to improvements.

The framework demonstrates scalable, trustworthy GEO across multiple engines.

Abstract

Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimize each instance in isolation, unable to accumulate or transfer effective strategies across tasks and engines. We reframe GEO as a strategy learning problem and propose MAGEO, a multi-agent framework in which coordinated planning, editing, and fidelity-aware evaluation serve as the execution layer, while validated editing patterns are progressively distilled into reusable, engine-specific optimization skills. To enable controlled assessment, we introduce a Twin Branch Evaluation Protocol for causal attribution of content edits and DSV-CF, a dual-axis metric that unifies semantic visibility with attribution accuracy. We further release MSME-GEO-Bench, a multi-scenario, multi-engine benchmark grounded in real-world queries. Experiments on three mainstream engines show that MAGEO substantially outperforms heuristic baselines in both visibility and citation fidelity, with ablations confirming that engine-specific preference modeling and strategy reuse are central to these gains, suggesting a scalable learning-driven paradigm for trustworthy GEO. Code is available at https://github.com/Wu-beining/MAGEO