LLM-Based Exploratory Testing Charter Generation:A Framework and Empirical Evaluation

LLM-Based Exploratory Testing Charter Generation:A Framework and Empirical Evaluation | 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 Exploratory Testing Charter Generation:A Framework and Empirical Evaluation Arbaz Surti This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9296494/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Exploratory testing is a widely adopted practice in software quality as-surance, yet the authoring of structured testing charters — the artefacts that guideexploratory sessions — remains an entirely manual activity. No automated approachto charter generation has been proposed or empirically evaluated in the literature. Thispaper presents the Exploratory Testing Charter Generator (ETCG), a framework thatapplies GPT-4o, a transformer-based large language model, to generate structuredexploratory testing charters from software requirement specifications. ETCG employsa four-component structured prompt architecture — role instruction, context injec-tion, output format constraint, and generation rules — to produce five charters perspecification in a validated JSON schema encoding target area, risk focus, exploratoryapproach, priority, and estimated session duration. We evaluate ETCG against two comparison conditions — a role-instructed inter-mediate baseline (same guidance, no schema) and an unstructured prompt baseline —across 25 specifications, scoring 375 charters (125 per condition) using a purpose-builtfive-dimension rubric (Specificity, Testability, Risk Coverage, Clarity, Actionability)with inter-rater reliability validated against an independent reviewer (observed agree-ment 97.2% within one scale point across 250 dimension ratings; n = 50 charters). Thetwo-baseline design reveals that role framing and explicit guidance (Intermediate con-dition) account for the primary quality gain over the unstructured baseline (+3.20pp,SD reduced from 14.54% to 8.23%), while the structured JSON output schema (ETCGversus Intermediate) contributes negligible mean difference (−0.26pp). No pairwiseoverall comparison reaches statistical significance due to a ceiling effect (72–80%of charters at maximum score). The schema’s contribution is dimension-specific:Risk Coverage improvement is driven by role framing and guidance (Intermediateversus Baseline, p = 0.013), while the schema slightly constrains Clarity relativeto a free-form guided prompt (ETCG versus Intermediate, p = 0.018). Preliminaryevidence suggests that input specification richness moderates framework performance:on structured specifications (n = 7 ), the framework achieves near-perfect quality and consistency (99.81% ± 1.13%); this finding warrants replication with a largerstructured-specification set. exploratory testing charter generation large language models generative AI prompt engineering software testing automation test planning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 11 May, 2026 Reviewers invited by journal 23 Apr, 2026 Editor assigned by journal 03 Apr, 2026 Submission checks completed at journal 03 Apr, 2026 First submitted to journal 01 Apr, 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-9296494","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629817198,"identity":"01c7243c-5960-44e7-8156-fba1703a11c4","order_by":0,"name":"Arbaz Surti","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIie3RMQrCMBSA4YSuUddM9goRQfAsLhWhTnHuoCWTLh6goNQr6NK5pVCXqKvSpS46u2X0VUF0qNVNMP+QhpKPJAQhne4nI09zy4HBMMTHBAtL5gR/Q/D4/n0LarNNdFEoQKbHz9nRH3VqEyDKCQoJ3Q56lKIUsX2/IbrBmnsx7DaVafE2kjDKckJtDCThAoiBx8XElKSpLCCml5N5whdlhEnSoiEQtM+JGPJlGWnIqt0WLCVMnrBnJSFfAYne3aUuK/FBOWndnNjoooYu93dxlMGf4uvfj/d4nfg2hiXrX3K/WazT6XR/0hXPV1mMr6Dd0wAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Arbaz","middleName":"","lastName":"Surti","suffix":""}],"badges":[],"createdAt":"2026-04-02 00:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9296494/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9296494/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108007786,"identity":"06942f3c-cefe-421a-a01e-f2b51ba64e24","added_by":"auto","created_at":"2026-04-28 13:01:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":242226,"visible":true,"origin":"","legend":"","description":"","filename":"LLMBasedExploratoryTestingCharterGenerationAFrameworkandEmpiricalEvaluation1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9296494/v1_covered_65c248b0-6dda-4960-9e9c-cc1676a20893.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LLM-Based Exploratory Testing Charter Generation:A Framework and Empirical Evaluation","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":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"exploratory testing, charter generation, large language models, generative AI, prompt engineering, software testing automation, test planning","lastPublishedDoi":"10.21203/rs.3.rs-9296494/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9296494/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eExploratory testing is a widely adopted practice in software quality as-surance, yet the authoring of structured testing charters — the artefacts that guideexploratory sessions — remains an entirely manual activity. No automated approachto charter generation has been proposed or empirically evaluated in the literature. Thispaper presents the Exploratory Testing Charter Generator (ETCG), a framework thatapplies GPT-4o, a transformer-based large language model, to generate structuredexploratory testing charters from software requirement specifications. ETCG employsa four-component structured prompt architecture — role instruction, context injec-tion, output format constraint, and generation rules — to produce five charters perspecification in a validated JSON schema encoding target area, risk focus, exploratoryapproach, priority, and estimated session duration.\u003c/p\u003e\n\u003cp\u003eWe evaluate ETCG against two comparison conditions — a role-instructed inter-mediate baseline (same guidance, no schema) and an unstructured prompt baseline —across 25 specifications, scoring 375 charters (125 per condition) using a purpose-builtfive-dimension rubric (Specificity, Testability, Risk Coverage, Clarity, Actionability)with inter-rater reliability validated against an independent reviewer (observed agree-ment 97.2% within one scale point across 250 dimension ratings; n = 50 charters). Thetwo-baseline design reveals that role framing and explicit guidance (Intermediate con-dition) account for the primary quality gain over the unstructured baseline (+3.20pp,SD reduced from 14.54% to 8.23%), while the structured JSON output schema (ETCGversus Intermediate) contributes negligible mean difference (−0.26pp). No pairwiseoverall comparison reaches statistical significance due to a ceiling effect (72–80%of charters at maximum score). The schema’s contribution is dimension-specific:Risk Coverage improvement is driven by role framing and guidance (Intermediateversus Baseline, p = 0.013), while the schema slightly constrains Clarity relativeto a free-form guided prompt (ETCG versus Intermediate, p = 0.018). Preliminaryevidence suggests that input specification richness moderates framework performance:on structured specifications (n = 7 ), the framework achieves near-perfect quality and consistency (99.81% ± 1.13%); this finding warrants replication with a largerstructured-specification set.\u003c/p\u003e","manuscriptTitle":"LLM-Based Exploratory Testing Charter Generation:A Framework and Empirical Evaluation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-28 11:58:47","doi":"10.21203/rs.3.rs-9296494/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"51367558167335918760361894311305577409","date":"2026-05-11T18:57:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-23T11:46:41+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-03T18:20:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-03T09:16:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Automated Software Engineering","date":"2026-04-02T00:04:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"13a22461-b0ec-4ca9-b2ee-08569ef56767","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"51367558167335918760361894311305577409","date":"2026-05-11T18:57:57+00:00","index":20,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-28T11:58:47+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 11:58:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9296494","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9296494","identity":"rs-9296494","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}