Code Broker A Multi Agent System for Automated Code Quality Assessment

Code Broker A Multi Agent System for Automated Code Quality Assessment | 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Article Code Broker A Multi Agent System for Automated Code Quality Assessment Samer Attrah This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9619569/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 We present Code Broker, a multi-agent system built with Google’s Agent Development Kit (ADK) that analyses Python code from files, local directories, or GitHub repositories and generates actionable quality assessment reports. The system employs a hierarchical five-agent architecture in which a root orchestrator coordinates a sequential pipeline agent, which in turn dispatches three specialised agents in parallel—a Correctness Assessor, a Style Assessor, and a Description Generator—before synthesising findings through an Improvement Recommender. Reports score four dimensions—correctness, security, style, and maintainability—and are rendered in both Markdown and HTML. Code Broker combines LLM-based reasoning with deterministic static-analysis signals from Pylint, uses asynchronous execution with retry logic to improve robustness, and explores lightweight session memory for retaining and querying prior assessment context. We position the paper as a technical report on system design and prompt/tool orchestration, and present a preliminary qualitative evaluation on representative Python codebases. The results suggest that parallel specialised agents produce readable, developer-oriented feedback, while also highlighting current limitations in evaluation depth, security tooling, large-repository handling, and the current use of only in-memory persistence. All code and reproducibility materials are available at [27]. Software Engineering Artificial Intelligence and Machine Learning AI Agents Code Quality Assessment Multi Agent Systems Software Engineering Google Agent Development Kit ADK Python. 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-9619569","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":634947635,"identity":"8f55e60d-d162-47ee-9edf-fdefe7ef9a00","order_by":0,"name":"Samer Attrah","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYJCCA2CSvf/hAyDFw0ekFgOg2jPMBiAtbERaBFQskcMmAWIS1CLffjrxcEXNn3z+GbnHKr/m2MmwMTA/fHQDn/FncjccPHPMwHLGmXdpt2W3JQMdxmZsnIPXRUAtDWwGBgzHE8xuS25jBmrhYZPGp0W+/y1Qyz8DA/kDCWbFktvqCWthuAG0pbHNwMDgRI4Z48dthwlrMbgBtKWxz9jA8MyxZGnGbcd52JgJ+EW+P3fzx4ZvcgZyx5sPfvy5rdqen7354WO8DkMGzDxgkljlIMD4gxTVo2AUjIJRMGIAAAx3S+SpJI9NAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0006-8090-1256","institution":"Independent researcher","correspondingAuthor":true,"prefix":"","firstName":"Samer","middleName":"","lastName":"Attrah","suffix":""}],"badges":[],"createdAt":"2026-05-05 14:04:23","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9619569/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9619569/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108813084,"identity":"815a2c45-d882-4a7b-bc5a-63b7c514c8e6","added_by":"auto","created_at":"2026-05-08 16:13:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":214660,"visible":true,"origin":"","legend":"","description":"","filename":"CodeBrokerPreprint.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9619569/v1_covered_052d8432-ad9f-4d3f-955d-ec5dee8bdec9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eCode Broker A Multi Agent System for Automated Code Quality Assessment\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Independent research","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":"AI Agents, Code Quality Assessment, Multi Agent Systems, Software Engineering, Google Agent Development Kit ADK, Python.","lastPublishedDoi":"10.21203/rs.3.rs-9619569/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9619569/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe present Code Broker, a multi-agent system built with Google’s Agent Development Kit (ADK) that analyses Python code from files, local directories, or GitHub repositories and generates actionable quality assessment reports. The system employs a hierarchical five-agent architecture in which a root orchestrator coordinates a sequential pipeline agent, which in turn dispatches three specialised agents in parallel—a Correctness Assessor, a Style Assessor, and a Description Generator—before synthesising findings through an Improvement Recommender. Reports score four dimensions—correctness, security, style, and maintainability—and are rendered in both Markdown and HTML. Code Broker combines LLM-based reasoning with deterministic static-analysis signals from Pylint, uses asynchronous execution with retry logic to improve robustness, and explores lightweight session memory for retaining and querying prior assessment context. We position the paper as a technical report on system design and prompt/tool orchestration, and present a preliminary qualitative evaluation on representative Python codebases. The results suggest that parallel specialised agents produce readable, developer-oriented feedback, while also highlighting current limitations in evaluation depth, security tooling, large-repository handling, and the current use of only in-memory persistence. All code and reproducibility materials are available at [27].\u003c/p\u003e","manuscriptTitle":"Code Broker A Multi Agent System for Automated Code Quality Assessment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 14:47:42","doi":"10.21203/rs.3.rs-9619569/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":"2bd1e4d1-5f97-477e-b511-47a2a267269a","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67579649,"name":"Software Engineering"},{"id":67579650,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-05-08T14:47:43+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 14:47:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9619569","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9619569","identity":"rs-9619569","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}