Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.19516 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910153830301696 |
|---|---|
| author | Wu, Beining Mao, Fuyou Lin, Jiong Yang, Cheng Lu, Jiaxuan Guo, Yifu Zhang, Siyu Wu, Yifan Huang, Ying Li, Fu |
| author_facet | Wu, Beining Mao, Fuyou Lin, Jiong Yang, Cheng Lu, Jiaxuan Guo, Yifu Zhang, Siyu Wu, Yifan Huang, Ying Li, Fu |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19516 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning Wu, Beining Mao, Fuyou Lin, Jiong Yang, Cheng Lu, Jiaxuan Guo, Yifu Zhang, Siyu Wu, Yifan Huang, Ying Li, Fu Artificial Intelligence 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 |
| title | From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.19516 |