CognAlign: A Multi-Agent Cognitive-Alignment Framework for Transparent, Bias-Aware Medical Triage Using Small Language Models

CognAlign: A Multi-Agent Cognitive-Alignment Framework for Transparent, Bias-Aware Medical Triage Using Small Language Models | 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 CognAlign: A Multi-Agent Cognitive-Alignment Framework for Transparent, Bias-Aware Medical Triage Using Small Language Models Nirvaan Duggirala, Aanya Pande This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8272448/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 CognAlign presents a modular, multi-agentic system designed to enhance transparency, bias-awareness, and adaptability in Small Language Models (SLMs) for high-stakes decision-making, particularly medical triage. By integrating cognitive dual-process reasoning, bias sentinels, and structured rationale generation, CognAlign enables SLMs to dynamically allocate computational resources, detect and mitigate bias, and produce interpretable outputs, supporting clinician oversight and equitable triage decisions. The system was evaluated on clinically validated triage cases, including mis-triaged “tricky” cases, supplemented by development datasets exceeding 1,000 samples. Performance was assessed across clinical accuracy, bias absence, patient safety, resource optimization, transparency, and routing latency. Compared to baseline SLMs, CognAlign reduced clinical errors by 24%, eliminated patient-safety violations, increased transparency from 0 to 0.489, and improved overall performance by 9.7%, while maintaining efficiency and bias-absence. Tricky cases were more consistently routed to System 2, demonstrating effective recognition of uncertainty and deeper reasoning. Lightweight deployment on phi-3 SLMs maintained high clinical reliability and bias mitigation without requiring cloud resources. Feedback from professionals across multiple healthcare systems indicates practical utility, enabling nurses to shift from direct triage to oversight and supporting phased adoption in less formalized systems. CognAlign demonstrates the potential of cognitive-aligned, low-compute SLMs to provide interpretable, bias-aware, and safe AI outputs. Future testing on larger datasets, across diverse SLMs, and alongside real-time clinician comparisons could expand robustness. Beyond medical triage, its architecture offers a transferable framework for critical decision-making domains, enabling transparency, fairness, and efficiency. Artificial Intelligence Small Language Models Computational Cognitive Science Systems Software Intelligent Machines Agentic Medical Triage 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-8272448","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":554809582,"identity":"13c78372-a451-4096-9daa-fa7af8a77076","order_by":0,"name":"Nirvaan Duggirala","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0006-0667-0285","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Nirvaan","middleName":"","lastName":"Duggirala","suffix":""},{"id":554809607,"identity":"7b7eee54-709c-469e-abd8-b94330a49b95","order_by":1,"name":"Aanya Pande","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Aanya","middleName":"","lastName":"Pande","suffix":""}],"badges":[],"createdAt":"2025-12-03 16:45:19","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-8272448/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8272448/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97669987,"identity":"caa94880-2e97-4ee7-a443-1f4798e30dd6","added_by":"auto","created_at":"2025-12-08 09:29:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":378453,"visible":true,"origin":"","legend":"","description":"","filename":"ReseachPaperCognAlign.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8272448/v1_covered_a1cd14c9-098d-43b9-bfd8-568a4d3e5ff1.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eCognAlign: A Multi-Agent Cognitive-Alignment Framework for Transparent, Bias-Aware Medical Triage Using Small Language Models\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Artificial Intelligence, Small Language Models, Computational Cognitive Science, Systems Software, Intelligent Machines, Agentic, Medical Triage","lastPublishedDoi":"10.21203/rs.3.rs-8272448/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8272448/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cem\u003eCognAlign presents a modular, multi-agentic system designed to enhance transparency, bias-awareness, and adaptability in Small Language Models (SLMs) for high-stakes decision-making, particularly medical triage. By integrating cognitive dual-process reasoning, bias sentinels, and structured rationale generation, CognAlign enables SLMs to dynamically allocate computational resources, detect and mitigate bias, and produce interpretable outputs, supporting clinician oversight and equitable triage decisions. The system was evaluated on clinically validated triage cases, including mis-triaged “tricky” cases, supplemented by development datasets exceeding 1,000 samples. Performance was assessed across clinical accuracy, bias absence, patient safety, resource optimization, transparency, and routing latency. Compared to baseline SLMs, CognAlign reduced clinical errors by 24%, eliminated patient-safety violations, increased transparency from 0 to 0.489, and improved overall performance by 9.7%, while maintaining efficiency and bias-absence. Tricky cases were more consistently routed to System 2, demonstrating effective recognition of uncertainty and deeper reasoning. Lightweight deployment on phi-3 SLMs maintained high clinical reliability and bias mitigation without requiring cloud resources. Feedback from professionals across multiple healthcare systems indicates practical utility, enabling nurses to shift from direct triage to oversight and supporting phased adoption in less formalized systems. CognAlign demonstrates the potential of cognitive-aligned, low-compute SLMs to provide interpretable, bias-aware, and safe AI outputs. Future testing on larger datasets, across diverse SLMs, and alongside real-time clinician comparisons could expand robustness. Beyond medical triage, its architecture offers a transferable framework for critical decision-making domains, enabling transparency, fairness, and efficiency.\u003c/em\u003e\u003c/p\u003e","manuscriptTitle":"CognAlign: A Multi-Agent Cognitive-Alignment Framework for Transparent, Bias-Aware Medical Triage Using Small Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-05 06:01:37","doi":"10.21203/rs.3.rs-8272448/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":"4c507990-339d-4fda-b767-08e941828b80","owner":[],"postedDate":"December 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-05T06:01:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-05 06:01:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8272448","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8272448","identity":"rs-8272448","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}