LLM-Driven Metaheuristic Innovation: An Adaptive Hybrid COA–LSHADE–MPA Algorithm

LLM-Driven Metaheuristic Innovation: An Adaptive Hybrid COA–LSHADE–MPA Algorithm | 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 Article LLM-Driven Metaheuristic Innovation: An Adaptive Hybrid COA–LSHADE–MPA Algorithm Fatme Ghaddar, Imtiaz Ahmad, Ayed Salman, Mohammad Alfailakawi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8915837/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 22 You are reading this latest preprint version Abstract The use of large language models (LLMs) as generators of metaheuristic algorithms introduces a new paradigm for automated algorithm design. This study proposes an LLM-generated algorithm called hybrid CLM, inspired by the crayfish optimization algorithm (COA), Success-History Based Adaptive Differential Evolution with Linear Population Size Reduction (LSHADE), and marine predator algorithm (MPA), and designed using GPT-4o via the evolution of heuristics prompting technique. The hybrid CLM switches between COA, LSHADE, and MPA features to guide population convergence and choice of optimization values. An ablation study of hybrid CLM comprising configurations was performed, followed by evaluation against COA, LSHADE, MPA, whale optimization algorithm (WOA), and sailfish optimization algorithm (SFO) across 64 CEC2017, CEC2022, and mathematical benchmark functions. Results reveal that the hybrid CLM algorithm delivers speed and accuracy, outperforming or matching rivals in 24 out of 29 CEC2017 benchmarks, 7 out of 12 CEC2022, and 12 out of 23 mathematical functions. In CEC2017, hybrid CLM’s execution time marked an overall 38% speed-up, six times faster than MPA, with insignificant fitness differences. Similar performance is attained on CEC2022 and mathematical functions. Overall, results demonstrate that this LLM-generated hybrid CLM can compete with human-designed optimizers while cutting execution time by up to 40%. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 16 Apr, 2026 Reviews received at journal 18 Mar, 2026 Reviews received at journal 13 Mar, 2026 Reviews received at journal 10 Mar, 2026 Reviews received at journal 08 Mar, 2026 Reviews received at journal 07 Mar, 2026 Reviews received at journal 06 Mar, 2026 Reviews received at journal 06 Mar, 2026 Reviewers agreed at journal 03 Mar, 2026 Reviewers agreed at journal 01 Mar, 2026 Reviewers agreed at journal 01 Mar, 2026 Reviews received at journal 28 Feb, 2026 Reviewers agreed at journal 28 Feb, 2026 Reviewers agreed at journal 28 Feb, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviewers invited by journal 26 Feb, 2026 Editor assigned by journal 26 Feb, 2026 Editor invited by journal 26 Feb, 2026 Submission checks completed at journal 25 Feb, 2026 First submitted to journal 25 Feb, 2026 You are reading this latest preprint version 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-8915837","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":599939395,"identity":"b42566bb-422e-479d-84db-0d483b00dece","order_by":0,"name":"Fatme Ghaddar","email":"","orcid":"","institution":"Kuwait University","correspondingAuthor":false,"prefix":"","firstName":"Fatme","middleName":"","lastName":"Ghaddar","suffix":""},{"id":599939396,"identity":"568c7792-c9ea-4e61-beb9-497c066faf47","order_by":1,"name":"Imtiaz Ahmad","email":"","orcid":"","institution":"Kuwait University","correspondingAuthor":false,"prefix":"","firstName":"Imtiaz","middleName":"","lastName":"Ahmad","suffix":""},{"id":599939397,"identity":"59cea97c-1535-4ffb-abef-dfdfd2c3eaa6","order_by":2,"name":"Ayed Salman","email":"","orcid":"","institution":"Kuwait University","correspondingAuthor":false,"prefix":"","firstName":"Ayed","middleName":"","lastName":"Salman","suffix":""},{"id":599939398,"identity":"3b921405-1802-4cd4-9c0a-4d93e9b3ae37","order_by":3,"name":"Mohammad Alfailakawi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIie3PMWuDQBTA8WcfxEVwvaX1KzwRJEPoZzkRnCwUAkVoIQdC1qwdSr5Dl8zCgS5+AEOGJnTN4JitfQqFLhccM9x/eHAHP94dgM12i7nOEeQzEICjAAo53PGhukIQCST9kXYqgZFwznoC8Ut0+iM9Rv57qu722yxRbrkT0GojERpRSEpj0SUKn3Z5orz6RUBnJqD9igku4DCSIlEijwX0B6MIeMtF0moRjOSDSXC+TkjjjLfomEai+GHCY9KZSchkLqmJwq+T0nmdRWsvW85l+2MkD02J+0vxGm7b5vSdv6X3G1d/dn2dmb//v2oYs2HIacBms9lshn4BLtJWA3+PbScAAAAASUVORK5CYII=","orcid":"","institution":"Kuwait University","correspondingAuthor":true,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Alfailakawi","suffix":""}],"badges":[],"createdAt":"2026-02-19 09:10:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8915837/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8915837/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107704668,"identity":"c482cad4-7407-45d6-8f70-9404e72add70","added_by":"auto","created_at":"2026-04-24 08:53:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":66248948,"visible":true,"origin":"","legend":"","description":"","filename":"LLMHybridCLMScientificreport.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8915837/v1_covered_a13379a2-f5ab-4f14-9a8f-0e020ef7ef14.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LLM-Driven Metaheuristic Innovation: An Adaptive Hybrid COA–LSHADE–MPA Algorithm","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8915837/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8915837/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The use of large language models (LLMs) as generators of metaheuristic algorithms introduces a new paradigm for automated algorithm design. This study proposes an LLM-generated algorithm called hybrid CLM, inspired by the crayfish optimization algorithm (COA), Success-History Based Adaptive Differential Evolution with Linear Population Size Reduction (LSHADE), and marine predator algorithm (MPA), and designed using GPT-4o via the evolution of heuristics prompting technique. The hybrid CLM switches between COA, LSHADE, and MPA features to guide population convergence and choice of optimization values. An ablation study of hybrid CLM comprising configurations was performed, followed by evaluation against COA, LSHADE, MPA, whale optimization algorithm (WOA), and sailfish optimization algorithm (SFO) across 64 CEC2017, CEC2022, and mathematical benchmark functions. Results reveal that the hybrid CLM algorithm delivers speed and accuracy, outperforming or matching rivals in 24 out of 29 CEC2017 benchmarks, 7 out of 12 CEC2022, and 12 out of 23 mathematical functions. In CEC2017, hybrid CLM’s execution time marked an overall 38% speed-up, six times faster than MPA, with insignificant fitness differences. Similar performance is attained on CEC2022 and mathematical functions. Overall, results demonstrate that this LLM-generated hybrid CLM can compete with human-designed optimizers while cutting execution time by up to 40%.","manuscriptTitle":"LLM-Driven Metaheuristic Innovation: An Adaptive Hybrid COA–LSHADE–MPA Algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-04 13:05:02","doi":"10.21203/rs.3.rs-8915837/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-16T08:02:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T13:37:33+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-13T11:18:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-10T09:29:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-09T00:52:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T13:18:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T02:32:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-06T06:37:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"327367866551195767709636043636925166074","date":"2026-03-03T11:16:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34382960488175519688312223915945805123","date":"2026-03-02T00:32:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59414578439722549315532335996153711415","date":"2026-03-01T06:34:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-01T01:34:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"128325876951552865360626608203240149544","date":"2026-03-01T01:28:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"196925435936980010201615888161979801004","date":"2026-02-28T23:02:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"160080020060619778913804838452119529569","date":"2026-02-27T03:04:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"186686322788905301488522989724668202790","date":"2026-02-27T01:54:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135358444633507742678631296398655883453","date":"2026-02-26T21:39:07+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-26T21:33:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-26T21:19:26+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-26T10:11:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-25T10:08:41+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-02-25T10:05:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ebf0e932-8815-4816-a672-534253732fab","owner":[],"postedDate":"March 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":63841281,"name":"Physical sciences/Engineering"},{"id":63841282,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-16T08:12:12+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-04 13:05:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8915837","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8915837","identity":"rs-8915837","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}