A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures

A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures Cheonsu Jeong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8139402/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract This study proposes the Self-Evolving Multi-Agent Framework (SEMAF) to address the prevalent issues of rigidity and knowledge drift in current Large Language Model (LLM)-based multi-agent systems. While existing frameworks rely on static, role-based collaboration, SEMAF introduces a dynamic and adaptive architecture that allows agents to continuously learn, self-diagnose, and reorganize their structure within dynamic environments. The core of SEMAF integrates three innovative components: a knowledge graph Layer for structured continuous knowledge integration and catastrophic forgetting mitigation, a multi-source feedback collector for generating quantitative reinforcement signals, and an Evolution Engine that drives self-improvement through collective reflection and policy optimization. Notably, SEMAF implements an Adaptation Layer that executes dynamic role reorganization to maintain collaborative efficiency when communication bottlenecks are detected. To enable systematic validation of self-evolving systems, this study proposes a comprehensive experimental methodology that includes three novel meta-metrics: the learning rate of adaptation (LRA), which measures adaptation speed; the collaboration efficiency (CE), which evaluates result quality against communication cost; and the knowledge retention index (KRI), which assesses knowledge consistency during continuous learning. The proposed evaluation framework provides protocols for environmental simulation, baseline comparison, statistical validation, and ablation studies. By offering both a theoretical framework for self-evolution and a rigorous methodology for empirical validation, this study makes a significant contribution to the advancement of autonomous, robust, and trustworthy AI systems. The proposed approach lays the foundation for future research on adaptive multi-agent architectures and provides generalized evaluation criteria applicable to various self-evolving AI systems. Artificial Intelligence and Machine Learning Self-Evolving Multi-Agent System Continuous Learning MAS Evaluation Methodology Adaptive Collaboration LLM Governance Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8139402","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":547452800,"identity":"875e494b-42d6-47c4-8fd3-328ad65ea525","order_by":0,"name":"Cheonsu Jeong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYLACCRDB3kCyFp4DpFuVQKRC/v4zBgwWFTZ58pHPH3668edwnrwD88NHN/CZfSPHgEHiTFqx4e0cY+nctsPFhgfYjI1z8GgxkOAxYJBsO5y4cXYOg3RuA5DRwMMmjVcLP9Bhkv+AKmcef/w75w8xWhiADpMEGj5fgsFMOocNyGAgoEXiRlrBAYljaYkbeHLMrHPb0hM3MBPwC3//4Y2PJWpsEue3H398O+ePNZDR/PAxPi0gcBgUlQYHYE49TEA5CDB+ABLyDVAenDEKRsEoGAWjAAoAoItM2U3OAuwAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-0751-3987","institution":"SAMSUNG SDS","correspondingAuthor":true,"prefix":"","firstName":"Cheonsu","middleName":"","lastName":"Jeong","suffix":""}],"badges":[],"createdAt":"2025-11-17 23:32:39","currentVersionCode":2,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8139402/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-8139402/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101205927,"identity":"b228828b-2423-4918-9313-a228f42b224a","added_by":"auto","created_at":"2026-01-27 09:50:33","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256309,"visible":true,"origin":"","legend":"","description":"","filename":"preprtSEMAF251117.docx","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/a8a2dbe89d2fbecfad559920.docx"},{"id":101205658,"identity":"026e2dc0-f35d-4703-ab43-5ecf6108d250","added_by":"auto","created_at":"2026-01-27 09:50:03","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs8139402.json","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/df6c23a6987a444f3757042a.json"},{"id":101146603,"identity":"4dc6d58f-645b-429f-b5ed-bdaae1ea3894","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125585,"visible":true,"origin":"","legend":"","description":"","filename":"rs81394020enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/471a8e832422b7d64513cdf5.xml"},{"id":101206110,"identity":"fab861b4-2418-4068-87cd-09d979f388ea","added_by":"auto","created_at":"2026-01-27 09:54:43","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/a10f988cc1414c36781dc8e5.jpeg"},{"id":101146593,"identity":"53dcc007-343d-4def-a8ee-9c32e64936de","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3049,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/aa6d5ee3fc1ca45430dc9cfd.png"},{"id":101205601,"identity":"0aae7bab-b1b1-4419-b2d5-a02240fdc15b","added_by":"auto","created_at":"2026-01-27 09:49:53","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52202,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/dab9e02c535ec0fda20d8458.png"},{"id":101205615,"identity":"47e0a906-c1ee-42c5-af6f-31662c61e9db","added_by":"auto","created_at":"2026-01-27 09:49:56","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11396,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/df78c159cc7899ad2e4a3c07.png"},{"id":101205578,"identity":"9005cdd9-e215-4a64-9cbe-42add3adf852","added_by":"auto","created_at":"2026-01-27 09:49:50","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7788,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/70fff7fb52ab2a8e42b16237.jpeg"},{"id":101146596,"identity":"e5a24535-6b33-4ecf-ae9b-4c1a6691a1e5","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1644,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/4a6fd8425ca9222edfe536b9.jpeg"},{"id":101205838,"identity":"90981c29-7824-40f0-a90d-5c5c6da254b7","added_by":"auto","created_at":"2026-01-27 09:50:21","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50001,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/6115d27b8060b7cf1db56b52.png"},{"id":101146599,"identity":"21ed0dde-1404-44b5-8522-93362aa74e3b","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21798,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/67ff51d9412c719856a2010b.png"},{"id":101206381,"identity":"8a686552-0beb-420f-8d5b-643f70092bd9","added_by":"auto","created_at":"2026-01-27 09:56:07","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5355,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/d8ae97b470788289a663b126.png"},{"id":101207047,"identity":"7fd68082-342e-47ac-85cd-fa686bf10193","added_by":"auto","created_at":"2026-01-27 09:57:11","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5324,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/8740c00eecec4eb61d17642d.png"},{"id":101206901,"identity":"8df1c114-8c03-45ee-98bd-7e3adf422b24","added_by":"auto","created_at":"2026-01-27 09:56:56","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3345,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/cb7b4655293246e9f8844493.png"},{"id":101146600,"identity":"89f5f712-b4f7-4ab2-9afb-c5818079173f","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2025,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/9b2f0f94cfe495668ba44a64.png"},{"id":101146604,"identity":"475abb73-6f2b-4fb8-9bfb-929c58cf61e5","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/030dcfcc1d45411d9e238190.png"},{"id":101146608,"identity":"eb81ee7c-52d7-40e3-8b5e-664f01429ff1","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1972,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/fb98db09a7eb6a707ea21f61.png"},{"id":101146606,"identity":"678e1e8c-0bdb-4d10-8613-90cb883855ed","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18345,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/25832fb7f093f87a6dd2d0b6.png"},{"id":101206902,"identity":"5ec37509-c83a-42ad-9666-abb7e6a10175","added_by":"auto","created_at":"2026-01-27 09:56:57","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4891,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/0e1336c651615a5c6285946f.png"},{"id":101205848,"identity":"581d44ac-7b8e-4e20-a205-9c9fddd99519","added_by":"auto","created_at":"2026-01-27 09:50:24","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1159,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/11c8cb6d654cac0e57357551.png"},{"id":101146610,"identity":"0131deb0-f674-4052-9f47-cfbfcf128385","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":960,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/e116925668c4dd15386b4244.png"},{"id":101206294,"identity":"82e9e4e8-10d9-4646-a9e0-79cccb4fece4","added_by":"auto","created_at":"2026-01-27 09:55:55","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16153,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/40f53fa73441e742b912b6e5.png"},{"id":101206995,"identity":"19a5cad5-a07c-45de-83ff-f0b82cde609a","added_by":"auto","created_at":"2026-01-27 09:57:06","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13536,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/e6ffcfe62d1aec51f957c57c.png"},{"id":101146612,"identity":"a3f730c6-74ed-4e81-9c9e-6cb049f98013","added_by":"auto","created_at":"2026-01-26 15:04:58","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2374,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/d397af5a90c588a26b77d7a7.png"},{"id":101146614,"identity":"f4bc8fad-f4e2-4c37-a0fa-d758213db554","added_by":"auto","created_at":"2026-01-26 15:04:59","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2302,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/ecfee5944d9cc4f67227a650.png"},{"id":101205983,"identity":"b20b460a-eea8-4941-8600-6378f8898eb8","added_by":"auto","created_at":"2026-01-27 09:50:53","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2119,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/1612b51a6b8adb701be40202.png"},{"id":101206374,"identity":"d0c4150a-390c-4601-9c0f-261881f8a584","added_by":"auto","created_at":"2026-01-27 09:56:06","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1431,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/4957eb231464bc847d191131.png"},{"id":101146613,"identity":"885051f0-3f65-49da-a5ef-1f444d4040bd","added_by":"auto","created_at":"2026-01-26 15:04:59","extension":"xml","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124431,"visible":true,"origin":"","legend":"","description":"","filename":"rs81394020structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/464676258b13bb8a94d51168.xml"},{"id":101146615,"identity":"56ff831b-25d4-4b68-a933-dcb45ef4d6e0","added_by":"auto","created_at":"2026-01-26 15:04:59","extension":"html","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139384,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2/63421ddc537b5eb527f62f4c.html"},{"id":101296715,"identity":"a0a8f2f1-174a-4b19-9052-b03527edc95d","added_by":"auto","created_at":"2026-01-28 09:19:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":520583,"visible":true,"origin":"","legend":"","description":"","filename":"prepSEMAFArchitecture.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8139402/v2_covered_e834ed52-2ff7-41c1-a763-15474a489f20.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"SAMSUNG","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Self-Evolving Multi-Agent System, Continuous Learning, MAS Evaluation Methodology, Adaptive Collaboration, LLM Governance","lastPublishedDoi":"10.21203/rs.3.rs-8139402/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8139402/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study proposes the Self-Evolving Multi-Agent Framework (SEMAF) to address the prevalent issues of rigidity and knowledge drift in current Large Language Model (LLM)-based multi-agent systems. While existing frameworks rely on static, role-based collaboration, SEMAF introduces a dynamic and adaptive architecture that allows agents to continuously learn, self-diagnose, and reorganize their structure within dynamic environments. The core of SEMAF integrates three innovative components: a knowledge graph Layer for structured continuous knowledge integration and catastrophic forgetting mitigation, a multi-source feedback collector for generating quantitative reinforcement signals, and an Evolution Engine that drives self-improvement through collective reflection and policy optimization. Notably, SEMAF implements an Adaptation Layer that executes dynamic role reorganization to maintain collaborative efficiency when communication bottlenecks are detected. To enable systematic validation of self-evolving systems, this study proposes a comprehensive experimental methodology that includes three novel meta-metrics: the learning rate of adaptation (LRA), which measures adaptation speed; the collaboration efficiency (CE), which evaluates result quality against communication cost; and the knowledge retention index (KRI), which assesses knowledge consistency during continuous learning. The proposed evaluation framework provides protocols for environmental simulation, baseline comparison, statistical validation, and ablation studies. By offering both a theoretical framework for self-evolution and a rigorous methodology for empirical validation, this study makes a significant contribution to the advancement of autonomous, robust, and trustworthy AI systems. The proposed approach lays the foundation for future research on adaptive multi-agent architectures and provides generalized evaluation criteria applicable to various self-evolving AI systems.\u003c/p\u003e","manuscriptTitle":"A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-01-26 15:04:47","doi":"10.21203/rs.3.rs-8139402/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2025-11-19 10:17:59","doi":"10.21203/rs.3.rs-8139402/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a519f406-0f41-4a39-a91a-8051cf3b1bcc","owner":[],"postedDate":"January 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58240706,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-11-19T10:17:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-26 15:04:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-8139402","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8139402","identity":"rs-8139402","version":["v2"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}