Addressing Trust Requirements in the Design of an Open-Source Multi-Agent LLM-Based Domain-Specific Chatbot

Addressing Trust Requirements in the Design of an Open-Source Multi-Agent LLM-Based Domain-Specific Chatbot | 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 Addressing Trust Requirements in the Design of an Open-Source Multi-Agent LLM-Based Domain-Specific Chatbot Jonatan Axetorn, Felix Edholm, Felix Dobslaw, Lucas Gren This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7494256/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Mar, 2026 Read the published version in Requirements Engineering → Version 1 posted 9 You are reading this latest preprint version Abstract Large Language Models (LLMs) have the potential to automate knowledge-intensive interactions in enterprise systems, yet their adoption is often limited. One reason is a lack of user trust. This study examines how trust can be systematically engineered into an LLM-driven, multi-agent chatbot that handles routine human-resources (HR) queries. We follow a two-cycle Design Science Research methodology. Cycle 1 triangulated a systematic literature review with a thematic analysis over semi-structured interviews of six employees at a global firm and a confirmatory workshop with five AI experts to elicit and validate trust requirements. Cycle II instantiated these requirements in a multi-agent LLM chatbot prototype artifact and evaluated whether the artifact satisfies them through controlled user sessions and expert walkthroughs, emphasizing perceived usefulness and trust captured in post-task interviews (n = 11) and operationalizing trust via alignment-oriented measures (faithfulness, answer relevancy, and adversarial robustness). The study yields a refined taxonomy of external (transparency, organizational safeguards, third-party security) and internal (model provenance, bias risk, reliability) trust factors, identifying reliability as the primary determinant of adoption. The implemented design achieved >= 0.86 on trust-aligned metrics and was endorsed by 9/11 participants as ready for field deployment. These findings demonstrate that trust can be proactively addressed through design and offer prescriptive guidelines for software engineers seeking to embed LLMs safely and responsibly in socio-technical contexts. LLM multi-agent LLM software system design trust Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Mar, 2026 Read the published version in Requirements Engineering → Version 1 posted Editorial decision: Revision requested 13 Oct, 2025 Reviews received at journal 10 Oct, 2025 Reviews received at journal 06 Oct, 2025 Reviewers agreed at journal 18 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers invited by journal 04 Sep, 2025 Editor assigned by journal 01 Sep, 2025 Submission checks completed at journal 01 Sep, 2025 First submitted to journal 30 Aug, 2025 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-7494256","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":511761659,"identity":"e30100f0-b7e4-4676-ab1f-e30736f27a62","order_by":0,"name":"Jonatan Axetorn","email":"","orcid":"","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jonatan","middleName":"","lastName":"Axetorn","suffix":""},{"id":511761660,"identity":"b15a816f-1a54-4556-8808-28c1ccee3062","order_by":1,"name":"Felix Edholm","email":"","orcid":"","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Felix","middleName":"","lastName":"Edholm","suffix":""},{"id":511761661,"identity":"db41d83a-d34c-4732-9e47-4d0a00341377","order_by":2,"name":"Felix Dobslaw","email":"","orcid":"","institution":"Mid Sweden University","correspondingAuthor":false,"prefix":"","firstName":"Felix","middleName":"","lastName":"Dobslaw","suffix":""},{"id":511761662,"identity":"4f92945d-5ca1-4098-b028-ae3f8ca05945","order_by":3,"name":"Lucas Gren","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYBACPgST+eABorSwITETSNbCY0CkFonkhx9/MNTm80v3fDjMU2NnLx99+NgDhhqbaNxa0oyleRiOW86cc3bDYZ5jyYkbz6WlGzAcS8ttwKklh0GageGYgcGN3A2HeRuYEwx7eMwkGBsO49PC/PMHUIv9jZwHQC319oY9/N8IaWGT4GGoMTAAWgfUcphxPg8PG34tPM/MrIFhZSBxI83g4JxjxxM38LCZSSTg8Qs/e/Ljmz8q6gz4ZyQ/fPCmptpevof5mcSHGhucWiDA4DAS+wCQSMCrHAzqEEx5/KaPglEwCkbBCAQA0PxSg0RNJFQAAAAASUVORK5CYII=","orcid":"","institution":"Chalmers University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Lucas","middleName":"","lastName":"Gren","suffix":""}],"badges":[],"createdAt":"2025-08-30 09:23:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7494256/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7494256/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00766-026-00457-w","type":"published","date":"2026-03-16T15:58:07+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":105223510,"identity":"d520e2ba-37ba-4d83-833f-90a7b8953493","added_by":"auto","created_at":"2026-03-23 16:07:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":446511,"visible":true,"origin":"","legend":"","description":"","filename":"BridgingTrustandDesignofaMultiAgentLLMBasedHRChatbotarXiv.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7494256/v1_covered_ccb93009-47ed-4127-ab40-6f4a7e695837.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Addressing Trust Requirements in the Design of an Open-Source Multi-Agent LLM-Based Domain-Specific Chatbot","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"requirements-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"reen","sideBox":"Learn more about [Requirements Engineering](http://link.springer.com/journal/766)","snPcode":"766","submissionUrl":"https://submission.springernature.com/new-submission/766/3","title":"Requirements Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"LLM, multi-agent LLM, software system design, trust","lastPublishedDoi":"10.21203/rs.3.rs-7494256/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7494256/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large Language Models (LLMs) have the potential to automate knowledge-intensive interactions in enterprise systems, yet their adoption is often limited. One reason is a lack of user trust. This study examines how trust can be systematically engineered into an LLM-driven, multi-agent chatbot that handles routine human-resources (HR) queries. We follow a two-cycle Design Science Research methodology. Cycle 1 triangulated a systematic literature review with a thematic analysis over semi-structured interviews of six employees at a global firm and a confirmatory workshop with five AI experts to elicit and validate trust requirements. Cycle II instantiated these requirements in a multi-agent LLM chatbot prototype artifact and evaluated whether the artifact satisfies them through controlled user sessions and expert walkthroughs, emphasizing perceived usefulness and trust captured in post-task interviews (n = 11) and operationalizing trust via alignment-oriented measures (faithfulness, answer relevancy, and adversarial robustness). The study yields a refined taxonomy of external (transparency, organizational safeguards, third-party security) and internal (model provenance, bias risk, reliability) trust factors, identifying reliability as the primary determinant of adoption. The implemented design achieved \u003e= 0.86 on trust-aligned metrics and was endorsed by 9/11 participants as ready for field deployment. These findings demonstrate that trust can be proactively addressed through design and offer prescriptive guidelines for software engineers seeking to embed LLMs safely and responsibly in socio-technical contexts.","manuscriptTitle":"Addressing Trust Requirements in the Design of an Open-Source Multi-Agent LLM-Based Domain-Specific Chatbot","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-10 17:04:30","doi":"10.21203/rs.3.rs-7494256/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-13T12:11:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-10T07:53:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T09:16:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"40075061451926180190306666182939196968","date":"2025-09-18T19:28:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"302323862480685124791784984215856015552","date":"2025-09-08T06:00:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-04T12:18:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-01T13:16:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-01T13:15:57+00:00","index":"","fulltext":""},{"type":"submitted","content":"Requirements Engineering","date":"2025-08-30T09:20:35+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"requirements-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"reen","sideBox":"Learn more about [Requirements Engineering](http://link.springer.com/journal/766)","snPcode":"766","submissionUrl":"https://submission.springernature.com/new-submission/766/3","title":"Requirements Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"60149ddc-29d3-4fe2-b28e-b61f55bd4ee9","owner":[],"postedDate":"September 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-23T16:04:36+00:00","versionOfRecord":{"articleIdentity":"rs-7494256","link":"https://doi.org/10.1007/s00766-026-00457-w","journal":{"identity":"requirements-engineering","isVorOnly":false,"title":"Requirements Engineering"},"publishedOn":"2026-03-16 15:58:07","publishedOnDateReadable":"March 16th, 2026"},"versionCreatedAt":"2025-09-10 17:04:30","video":"","vorDoi":"10.1007/s00766-026-00457-w","vorDoiUrl":"https://doi.org/10.1007/s00766-026-00457-w","workflowStages":[]},"version":"v1","identity":"rs-7494256","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7494256","identity":"rs-7494256","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}