ARXIV:2604.19516 · GENERATIVE AI OPTIMIZATION · SUBMITTED 22 APR · 20:32 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields available

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

Beining Wu · Fuyou Mao · Jiong Lin · Cheng Yang · Jiaxuan Lu · Yifu Guo · +4 at arXiv

A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

Ship in 2-4 weeks›Score7.0Evidence verified

Opportunity summary

Pain A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

Evidence 0 refs | 4 sources | 83% coverage

Blocker Evidence verified

Open Build Read PDF Signal Canvas Track

PROBLEM

A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy. We reframe GEO as a strategy learning problem and propose MAGEO, a multi-agent framework in…

METHOD

Full 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

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. 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…

WHY NOW

Generative AI Optimization moved forward this cycle; last verified April 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainA multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

Evidence0 refs | 4 sources | 83% coverage

Blockerno shell-level blocker reported

Analysis summary

A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields available

Competitive landscape

A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

Segment

Generative AI Optimization

Adoption evidence

Public code linked for build inspection

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "a5d97a39-a0c7-4996-88d7-73dc5fb53dd1", "arxiv_id": "2604.19516", "canonical_route": "/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "endpoints": { "paper_pack": "/api/v1/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning/paper-pack", "build_passport": "/api/v1/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning", "normalized_query": "2604.19516", "route": "/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "paper_ref": "from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning#webpage", "url": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "name": "From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning", "description": "A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning#scholarlyArticle", "headline": "From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning", "description": "A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.", "url": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning", "sameAs": "https://arxiv.org/abs/2604.19516", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2604.19516" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-04-21T14:39:24.000Z", "author": [ { "@type": "Person", "name": "Beining Wu" }, { "@type": "Person", "name": "Fuyou Mao" }, { "@type": "Person", "name": "Jiong Lin" }, { "@type": "Person", "name": "Cheng Yang" }, { "@type": "Person", "name": "Jiaxuan Lu" }, { "@type": "Person", "name": "Yifu Guo" }, { "@type": "Person", "name": "Siyu Zhang" }, { "@type": "Person", "name": "Yifan Wu" }, { "@type": "Person", "name": "Ying Huang" }, { "@type": "Person", "name": "Fu Li" } ], "codeRepository": "https://github.com/Wu-beining/MAGEO", "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 7 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Generative AI Optimization" }, { "@type": "PropertyValue", "propertyID": "commercialReadiness", "value": "code, repo url" } ] }, { "@type": "SoftwareSourceCode", "@id": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning#software", "name": "From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning - Source Code", "description": "A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.", "codeRepository": "https://github.com/Wu-beining/MAGEO", "url": "https://github.com/Wu-beining/MAGEO" }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Generative AI Optimization", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "From Experience to Skill: Multi-Agent Generative Engine Opti", "item": "https://sciencetostartup.com/paper/from-experience-to-skill-multi-agent-generative-engine-optimization-via-reusable-strategy-learning" } ] } ] }

Competitive landscape

A multi-agent framework that learns and reuses optimization strategies for generative engines to improve answer quality and citation accuracy.

Segment

Generative AI Optimization

Adoption evidence

Public code linked for build inspection

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

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

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

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline