Automated Algorithmic Discovery for Gravitational-Wave Detection Guided by LLM-Informed Evolutionary Monte Carlo Tree Search

Automated Algorithmic Discovery for Gravitational-Wave Detection Guided by LLM-Informed Evolutionary Monte Carlo Tree Search | 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 Automated Algorithmic Discovery for Gravitational-Wave Detection Guided by LLM-Informed Evolutionary Monte Carlo Tree Search He Wang, Liang Zeng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7478361/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Gravitational-wave signal detection with unknown source parameters buried in dynamic detector noise remains a formidable computational challenge. Existing approaches face core limitations from restrictive assumptions: traditional methods rely on predefined theoretical priors, while neural networks introduce hidden biases and lack interpretability. We propose Evolutionary Monte Carlo Tree Search (Evo-MCTS), the first integration of large language model (LLM) guidance with domain-aware physical constraints for automated gravitational wave detection. This framework systematically explores algorithmic solution spaces through tree-structured search enhanced by evolutionary optimization, combining MCTS for strategic exploration with evolutionary algorithms for solution refinement. The LLM component provides domain-aware heuristics while maintaining interpretability through explicit algorithmic pathway generation. Experimental validation demonstrates substantial performance improvements, achieving a 20.2% improvement over state-of-the-art gravitational wave detection algorithms on the MLGWSC-1 benchmark dataset and a remarkable 59.1% improvement over other LLM-based algorithm optimization frameworks. Beyond performance improvements, our framework establishes a transferable methodology for automated algorithmic discovery across computational science domains. Physical sciences/Mathematics and computing/Computational science Physical sciences/Physics/Astronomy and astrophysics/General relativity and gravity Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supp.pdf Supplementary Material Cite Share Download PDF Status: Under Review Version 1 posted 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-7478361","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":530281997,"identity":"a046e15b-0e02-4753-aded-a574f55232b2","order_by":0,"name":"He Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYBACAwhlQ7qWNNK1HCZBizl7j+Hngl/nE/vbjz9g+FHDIG9OSItlzxlj6Zl9txNnnMkxYOw5xmC4s4GQw27kbpDm7bmduIEhh4GBt4EhweAAIS33327+zdtzLnED//MHjH+J0nKDd5s0z48DiRskEgyYibPlTP43a96GZOMZN94YHJY5JmG4gaCW48eSb/P8sZPt709/+PBNjY08QVvAgLENQgMVSxCjHgT+EKtwFIyCUTAKRiQAAJZhQ3dcHrWdAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-1353-391X","institution":"University of Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"He","middleName":"","lastName":"Wang","suffix":""},{"id":530281998,"identity":"c6520e07-f143-41a7-b1b1-4daa90173214","order_by":1,"name":"Liang Zeng","email":"","orcid":"https://orcid.org/0000-0003-2295-2996","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Liang","middleName":"","lastName":"Zeng","suffix":""}],"badges":[],"createdAt":"2025-08-28 09:00:51","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7478361/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7478361/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96246732,"identity":"191873ad-57cf-47a9-870b-c4ea8551ce91","added_by":"auto","created_at":"2025-11-19 07:26:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3511803,"visible":true,"origin":"","legend":"Article File","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7478361/v1_covered_c586c768-b67a-4e0f-a1ff-ef89d5fdb7bb.pdf"},{"id":96040017,"identity":"a1d9d3f4-f448-44bb-a097-f6b1c8423099","added_by":"auto","created_at":"2025-11-17 03:54:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2106167,"visible":true,"origin":"","legend":"Supplementary Material","description":"","filename":"supp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7478361/v1/020b51b2d1273bfd05e97d25.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Automated Algorithmic Discovery for Gravitational-Wave Detection Guided by LLM-Informed Evolutionary Monte Carlo Tree Search","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7478361/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7478361/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Gravitational-wave signal detection with unknown source parameters buried in dynamic detector noise remains a formidable computational challenge. Existing approaches face core limitations from restrictive assumptions: traditional methods rely on predefined theoretical priors, while neural networks introduce hidden biases and lack interpretability. We propose Evolutionary Monte Carlo Tree Search (Evo-MCTS), the first integration of large language model (LLM) guidance with domain-aware physical constraints for automated gravitational wave detection. This framework systematically explores algorithmic solution spaces through tree-structured search enhanced by evolutionary optimization, combining MCTS for strategic exploration with evolutionary algorithms for solution refinement. The LLM component provides domain-aware heuristics while maintaining interpretability through explicit algorithmic pathway generation. Experimental validation demonstrates substantial performance improvements, achieving a 20.2% improvement over state-of-the-art gravitational wave detection algorithms on the MLGWSC-1 benchmark dataset and a remarkable 59.1% improvement over other LLM-based algorithm optimization frameworks. Beyond performance improvements, our framework establishes a transferable methodology for automated algorithmic discovery across computational science domains.","manuscriptTitle":"Automated Algorithmic Discovery for Gravitational-Wave Detection Guided by LLM-Informed Evolutionary Monte Carlo Tree Search","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-17 03:54:32","doi":"10.21203/rs.3.rs-7478361/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6aa8bcc2-30e7-4abb-a53f-655d31d7688f","owner":[],"postedDate":"November 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":56371966,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":56371967,"name":"Physical sciences/Physics/Astronomy and astrophysics/General relativity and gravity"}],"tags":[],"updatedAt":"2025-11-17T03:54:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-17 03:54:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7478361","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7478361","identity":"rs-7478361","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}