GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching

GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching | 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 GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching Haoran Wang, Pingzhi Li, Min Chen, Jinglei Cheng, Junyu Liu, Tianlong Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8816953/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Quantum computing is an exciting non-Von Neu-mann paradigm, offering provable speedups over classical computing for specific problems. However, the practical limits of classical simulatability for quantum circuits remain unclear, especially with current noisy quantum devices. In this work, we explore the potential of leveraging Large Language Models (LLMs) to simulate the output of a quantum Turing machine using Grover’s quantum circuits, known to provide quadratic speedups over classical counterparts. To this end, we developed GroverGPT, a specialized model based on LLaMA’s 8-billion-parameter architecture, trained on over 15 trillion tokens. Unlike brute-force state-vector simulations, which demand substantial computational resources, GroverGPT employs pattern recognition to approximate quantum search algorithms without explicitly representing quantum states. Analyzing 97K quantum search instances, GroverGPT consistently outperformed OpenAI’s GPT-4o (45% accuracy), achieving nearly 100% accuracy on 6-and 10-qubit datasets when trained on 4-qubit or larger datasets. It also demonstrated strong generalization, surpassing 95% accuracy for systems with over 20 qubits when trained on 3-to 6-qubit data. Analysis indicates GroverGPT captures quantum features of Grover’s search rather than classical patterns, supported by novel prompting strategies to enhance performance. Although accuracy declines with increasing system size, these findings offer insights into the practical boundaries of classical simulatability. This work suggests task-specific LLMs can surpass general-purpose models like GPT-4o in quantum algorithm learning and serve as powerful tools for advancing quantum research. Physical sciences/Mathematics and computing Physical sciences/Physics Full Text Additional Declarations Competing interest reported. J.L. is an associate editor of npj Quantum Information, but were not involved in the editorial review of, or the decision to publish this article. All other authors declare no competing interests. Cite Share Download PDF Status: Posted 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-8816953","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":601425379,"identity":"fc254786-bcc7-4f08-9003-a0e40b4aa00c","order_by":0,"name":"Haoran Wang","email":"","orcid":"","institution":"The University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Wang","suffix":""},{"id":601425380,"identity":"d14cd857-cf0b-4c95-bf3f-0cb14b2357e5","order_by":1,"name":"Pingzhi Li","email":"","orcid":"","institution":"The University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Pingzhi","middleName":"","lastName":"Li","suffix":""},{"id":601425381,"identity":"09840f57-0f19-45b8-89aa-b74b836cc026","order_by":2,"name":"Min Chen","email":"","orcid":"","institution":"The University of Pittsburgh","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Chen","suffix":""},{"id":601425382,"identity":"43300a5b-7289-4883-b72a-e7d2d72ebb40","order_by":3,"name":"Jinglei Cheng","email":"","orcid":"","institution":"The University of Pittsburgh","correspondingAuthor":false,"prefix":"","firstName":"Jinglei","middleName":"","lastName":"Cheng","suffix":""},{"id":601425383,"identity":"5ddc7b00-d00e-49bd-89de-1c989079d98e","order_by":4,"name":"Junyu Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYBACxgYQWSDBwA9lQkjCWgwkGCQbGBsbDhCjBQIMgOgAUDVRWphn5B6T5jGwSNx8u7n98QcGG9kNBwg5bEZeGlCLROK2OwdBDkszJkJLjhlEy41EkJbDicRr2TwDrOU/CVo2SIC1HCBCS88bY8s5BhLGM4B+mXHGINl4JiEthu05hjfeVNTJ9s9uf/ChosJOto+glgYGFgkwC0waEFAOAvLAqPmA0DIKRsEoGAWjAAsAAD9SR8UxWraDAAAAAElFTkSuQmCC","orcid":"","institution":"The University of Pittsburgh","correspondingAuthor":true,"prefix":"","firstName":"Junyu","middleName":"","lastName":"Liu","suffix":""},{"id":601425384,"identity":"c84db330-93cf-4ea4-8c62-a13774e4a433","order_by":5,"name":"Tianlong Chen","email":"","orcid":"","institution":"The University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Tianlong","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2026-02-07 16:38:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8816953/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8816953/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106420466,"identity":"87a79d87-007c-408c-a783-47f74d793b4b","added_by":"auto","created_at":"2026-04-08 11:03:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1231437,"visible":true,"origin":"","legend":"","description":"","filename":"npjQuantumQuantumFoundationModel.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8816953/v1_covered_e782cdf0-da64-40ac-809f-876235fc32ab.pdf"}],"financialInterests":"Competing interest reported. J.L. is an associate editor of npj Quantum Information, but were not involved in the editorial review of, or the decision to publish this article. All other authors declare no competing interests.","formattedTitle":"GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-8816953/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8816953/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Quantum computing is an exciting non-Von Neu-mann paradigm, offering provable speedups over classical computing for specific problems. However, the practical limits of classical simulatability for quantum circuits remain unclear, especially with current noisy quantum devices. In this work, we explore the potential of leveraging Large Language Models (LLMs) to simulate the output of a quantum Turing machine using Grover’s quantum circuits, known to provide quadratic speedups over classical counterparts. To this end, we developed GroverGPT, a specialized model based on LLaMA’s 8-billion-parameter architecture, trained on over 15 trillion tokens. Unlike brute-force state-vector simulations, which demand substantial computational resources, GroverGPT employs pattern recognition to approximate quantum search algorithms without explicitly representing quantum states. Analyzing 97K quantum search instances, GroverGPT consistently outperformed OpenAI’s GPT-4o (45% accuracy), achieving nearly 100% accuracy on 6-and 10-qubit datasets when trained on 4-qubit or larger datasets. It also demonstrated strong generalization, surpassing 95% accuracy for systems with over 20 qubits when trained on 3-to 6-qubit data. Analysis indicates GroverGPT captures quantum features of Grover’s search rather than classical patterns, supported by novel prompting strategies to enhance performance. Although accuracy declines with increasing system size, these findings offer insights into the practical boundaries of classical simulatability. This work suggests task-specific LLMs can surpass general-purpose models like GPT-4o in quantum algorithm learning and serve as powerful tools for advancing quantum research.","manuscriptTitle":"GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-06 06:03:54","doi":"10.21203/rs.3.rs-8816953/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":"8d20e7d5-32ab-4b1f-ac2e-c1cca8182855","owner":[],"postedDate":"March 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64005752,"name":"Physical sciences/Mathematics and computing"},{"id":64005753,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2026-04-08T11:03:26+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-06 06:03:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8816953","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8816953","identity":"rs-8816953","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}