From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
For practitioners optimizing content for generative engines, MAGEO introduces a scalable learning-driven paradigm that replaces isolated instance optimization with reusable strategy learning.
MAGEO reframes Generative Engine Optimization as a strategy learning problem, using a multi-agent framework to accumulate reusable optimization skills across tasks and engines. On three mainstream engines, it substantially outperforms heuristic baselines in both visibility and citation fidelity.
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