LLM-based Fuzzy Agent for Human-Machine Interaction in STEM Education and Taiwanese-English Co-Learning Application

LLM-based Fuzzy Agent for Human-Machine Interaction in STEM Education and Taiwanese-English Co-Learning Application | 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 LLM-based Fuzzy Agent for Human-Machine Interaction in STEM Education and Taiwanese-English Co-Learning Application Chang-Shing Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6301579/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 This paper presents a Large Language Model (LLM)-based fuzzy agent framework designed to enhance Human-Machine Interaction (HMI) in Quantum Computational Intelligence (QCI) and Artificial Intelligence (AI) learning, as well as Taiwanese-English co-learning. By integrating QCI&AI STEM experiential learning with language co-learning applications, the framework creates an adaptive and personalized learning environment using fuzzy logic-based Human Intelligence (HI) and evolutionary computation-based Machine Intelligence (MI). The framework comprises three main components: (1) the QCI&AI STEM experiential learning agent , which integrates QCI software and AI-driven models to facilitate interactive STEM learning; (2) the Trustworthy AI Dialogue Engine ( TAIDE ) -based Taiwanese-English co-learning agent , which utilizes the Meta AI UST model, TAIDE, and fine-tuned Open AI Whisper-Taiwanese model for real-time Taiwanese-English co-learning; and (3) the fuzzy Knowledge Graph (KG) agent , which constructs teacher’s and learners’ knowledge graphs to evaluate the students’ learning performance. Besides, an HMI-based Observation with Comfortable Intelligence ( HMI-OwCI ) model is proposed to create intelligent technologies that are seamlessly integrated and intuitively aligned with human needs. Additionally, two supporting agents enhance the proposed framework: the Genetic Algorithm-based Neural Network (GANN) Agent , which optimizes QCI learning models, and the LLM fine-tuned agent , which refines Taiwanese-English co-learning and generates various Whisper-Taiwanese models . Experimental results highlight that GANN adapts well in QCI&AI STEM learning, Whisper-Taiwanese models generalize effectively, and the fuzzy KG agent enables adaptive learning assessments. Human-Machine Co-Learning Quantum Computational Intelligence Fuzzy Knowledge Graph Agent STEM Large Language Model Trustworthy AI Dialogue Engine (TAIDE) Full Text Additional Declarations The 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-6301579","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":433609230,"identity":"eeff21f6-0d8d-414d-a3a7-482fa6b3e9fc","order_by":0,"name":"Chang-Shing Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYBACPjBZwcDAxg4XS8CvhQ1MngEymOGqgcQBQloY24AE8VrYmw9+/DlvmzwfMwPbY94fdxj42XMMmD+24dHCcyxZmnfbbcM2ZgZ2Y56EZwySPW8MGA7i0yKRY8bMuO02I1ALmzRPwmEGgxs5QC3b8GiRf/+N8eec2/ZwLfYEtUjwsDHwNtxORNgiQUgLT5qxNM+x28ltzIxtknPSDvNInHlWcODsP9xa+NkPP/z4o+a27fz25mMSb2wOy/G3J298UHEGtxYkwNgAInlAxAGiNIyCUTAKRsEowAkAlj9IAXZ8CywAAAAASUVORK5CYII=","orcid":"","institution":"National University of Tainan, Taiwan","correspondingAuthor":true,"prefix":"","firstName":"Chang-Shing","middleName":"","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2025-03-25 08:16:01","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-6301579/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6301579/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79321662,"identity":"23e1e047-2aa0-4796-a69b-391e7de5234d","added_by":"auto","created_at":"2025-03-27 04:34:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1105775,"visible":true,"origin":"","legend":"","description":"","filename":"LLMFuzzyAgentIJFS031320256.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6301579/v1_covered_5c3c2e7f-ed6d-4ce5-877d-720d3146df82.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLLM-based Fuzzy Agent for Human-Machine Interaction in STEM Education and Taiwanese-English Co-Learning Application\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"National University of Tainan","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":"Human-Machine Co-Learning, Quantum Computational Intelligence, Fuzzy Knowledge Graph Agent, STEM, Large Language Model, Trustworthy AI Dialogue Engine (TAIDE)","lastPublishedDoi":"10.21203/rs.3.rs-6301579/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6301579/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a Large Language Model (LLM)-based fuzzy agent framework designed to enhance Human-Machine Interaction (HMI) in Quantum Computational Intelligence (QCI) and Artificial Intelligence (AI) learning, as well as Taiwanese-English co-learning. By integrating QCI\u0026amp;AI STEM experiential learning with language co-learning applications, the framework creates an adaptive and personalized learning environment using fuzzy logic-based Human Intelligence (HI) and evolutionary computation-based Machine Intelligence (MI). The framework comprises three main components: (1) the \u003cem\u003eQCI\u0026amp;AI STEM\u003c/em\u003e \u003cem\u003eexperiential learning agent\u003c/em\u003e, which integrates QCI software and AI-driven models to facilitate interactive STEM learning; (2) the \u003cem\u003eTrustworthy AI Dialogue Engine \u003c/em\u003e(\u003cem\u003eTAIDE\u003c/em\u003e)\u003cem\u003e-based Taiwanese-English co-learning agent\u003c/em\u003e, which utilizes the \u003cem\u003eMeta AI UST\u003c/em\u003emodel, TAIDE, and \u003cem\u003efine-tuned\u003c/em\u003e \u003cem\u003eOpen AI Whisper-Taiwanese\u003c/em\u003e model for real-time Taiwanese-English co-learning; and (3) the \u003cem\u003efuzzy Knowledge Graph (KG) agent\u003c/em\u003e, which constructs teacher’s and learners’ knowledge graphs to evaluate the students’ learning performance. Besides, an \u003cem\u003eHMI-based Observation with Comfortable Intelligence\u003c/em\u003e (\u003cem\u003eHMI-OwCI\u003c/em\u003e) model is proposed to create intelligent technologies that are seamlessly integrated and intuitively aligned with human needs. Additionally, two supporting agents enhance the proposed framework: the \u003cem\u003eGenetic Algorithm-based Neural Network (GANN) Agent\u003c/em\u003e, which optimizes QCI learning models, and the \u003cem\u003eLLM fine-tuned agent\u003c/em\u003e, which refines Taiwanese-English co-learning and generates various \u003cem\u003eWhisper-Taiwanese models\u003c/em\u003e. Experimental results highlight that GANN adapts well in \u003cem\u003eQCI\u0026amp;AI STEM\u003c/em\u003e learning, \u003cem\u003eWhisper-Taiwanese\u003c/em\u003emodels generalize effectively, and the \u003cem\u003efuzzy KG agent \u003c/em\u003eenables adaptive learning assessments.\u003c/p\u003e","manuscriptTitle":"LLM-based Fuzzy Agent for Human-Machine Interaction in STEM Education and Taiwanese-English Co-Learning Application","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-27 04:25:52","doi":"10.21203/rs.3.rs-6301579/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":"daf254ed-c508-44da-85dc-8d3d13902db3","owner":[],"postedDate":"March 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-27T04:25:52+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-27 04:25:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6301579","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6301579","identity":"rs-6301579","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}