TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots

TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots | 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 Article TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots Hongyu Zhao, Tianyu Liu, Simeng Han, Tinglin Huang, Hua Xu, Weihao Xuan, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8098264/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Advances in AI have introduced several strong models in computational pathology to usher it into the era of multi-modal diagnosis, analysis, and interpretation. However, the current pathology-specific visual language models still lack capacities in making diagnosis with rigorous reasoning paths as well as handling divergent tasks, and thus challenges of building AI Copilots for real scenarios still exist. Here we introduce TeamPath, an AI system powered by reinforcement learning and router-enhanced solutions based on large-scale histopathology multimodal datasets, to work as a virtual assistant for expert-level disease diagnosis, patch-level information summarization, and cross-modality generation to integrate transcriptomic information for the clinical usage. We also collaborate with pathologists from Yale School of Medicine to demonstrate that TeamPath can assist them in working more efficiently by identifying and correcting expert conclusions and reasoning paths. Overall, TeamPath can flexibly choose the best settings according to the needs, and serve as an innovative and reliable system for information communication across different modalities and experts. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Cancer/Cancer genomics Histopathology Analysis Pathology Foundation Model Cancer Diagnosis Large Language Model Visual Language Model Large Reasoning Model Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-8098264","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":551982050,"identity":"1cbaf248-1c34-4c09-8df7-9b668ea0baa6","order_by":0,"name":"Hongyu Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYBACAyQG4wMGBgsUQYJamIFYgjQtbBJEaTFn7z38mreNwd6c/fCxap4aCTkG9uZtEvi0WPacS7MGamG27ElLu81zTMKYgedYGV4tBjdyzIyBWtgMDuSY3eZhk0hskMgxI0oLj8H5N2bFPP8k6hvk3xDUYvwYqEUCpJeZt00igUGCh4CWM2fMGOeckzAwuPEsWXJun4RhG09asQVeLcd7jD+8KbOxNziffPDDm2828vzshzfewKcFCNikeCDRwcDEA+ISUA4CzB9/QFmMP/AqHAWjYBSMgpEKAAR3QO4h1DXsAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-1195-9607","institution":"Yale University","correspondingAuthor":true,"prefix":"","firstName":"Hongyu","middleName":"","lastName":"Zhao","suffix":""},{"id":551982051,"identity":"d86b6651-74e0-4c6d-9351-65cca4465004","order_by":1,"name":"Tianyu Liu","email":"","orcid":"https://orcid.org/0000-0002-9412-6573","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Tianyu","middleName":"","lastName":"Liu","suffix":""},{"id":551982052,"identity":"46084911-2154-44a9-8717-d96cba58d49f","order_by":2,"name":"Simeng Han","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Simeng","middleName":"","lastName":"Han","suffix":""},{"id":551982053,"identity":"786f2268-0b93-4ece-8370-b58e985edbb2","order_by":3,"name":"Tinglin Huang","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Tinglin","middleName":"","lastName":"Huang","suffix":""},{"id":551982054,"identity":"d5548195-5e75-4d93-9220-9adbe9fe6732","order_by":4,"name":"Hua Xu","email":"","orcid":"https://orcid.org/0000-0002-5274-4672","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"Xu","suffix":""},{"id":551982055,"identity":"38ead9c0-c151-4d03-a4aa-590e5a01fc51","order_by":5,"name":"Weihao Xuan","email":"","orcid":"","institution":"RIKEN","correspondingAuthor":false,"prefix":"","firstName":"Weihao","middleName":"","lastName":"Xuan","suffix":""},{"id":551982056,"identity":"06a5d78c-1ed0-44c2-b389-5d8b8998f357","order_by":6,"name":"Heli Qi","email":"","orcid":"","institution":"RIKEN","correspondingAuthor":false,"prefix":"","firstName":"Heli","middleName":"","lastName":"Qi","suffix":""},{"id":551982057,"identity":"7c63b3ba-4060-4408-b4e6-61253caa0462","order_by":7,"name":"Irene Li","email":"","orcid":"","institution":"The University of Tokyo","correspondingAuthor":false,"prefix":"","firstName":"Irene","middleName":"","lastName":"Li","suffix":""},{"id":551982058,"identity":"641ded02-be7a-45f7-9e03-246bbd9a2ba0","order_by":8,"name":"Rui Yang","email":"","orcid":"https://orcid.org/0009-0006-0597-7197","institution":"Duke-NUS Medical School","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Yang","suffix":""},{"id":551982059,"identity":"bfdcc1fd-24a4-4919-bf84-4a1360cd05c7","order_by":9,"name":"Nan Liu","email":"","orcid":"https://orcid.org/0000-0003-3610-4883","institution":"Duke-NUS Medical School","correspondingAuthor":false,"prefix":"","firstName":"Nan","middleName":"","lastName":"Liu","suffix":""},{"id":551982060,"identity":"1a8f364a-3c3d-42e5-a75a-e1fc3047a490","order_by":10,"name":"Fang Wu","email":"","orcid":"https://orcid.org/0000-0001-7240-3915","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Fang","middleName":"","lastName":"Wu","suffix":""},{"id":551982061,"identity":"d733d9e4-9aae-45ad-aeff-d375936b9ef8","order_by":11,"name":"Hao Wu","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Wu","suffix":""},{"id":551982062,"identity":"98ad8c52-b667-40c0-833c-79dbdb578855","order_by":12,"name":"Peter Humphrey","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Humphrey","suffix":""},{"id":551982063,"identity":"9d861f97-8059-40e9-b53f-24c75ceac744","order_by":13,"name":"Marcello DiStasio","email":"","orcid":"https://orcid.org/0000-0001-6588-0713","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Marcello","middleName":"","lastName":"DiStasio","suffix":""}],"badges":[],"createdAt":"2025-11-12 16:17:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8098264/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8098264/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97229395,"identity":"a6d64105-203f-49ca-aca8-f4a68ba82468","added_by":"auto","created_at":"2025-12-02 09:06:34","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5082388,"visible":true,"origin":"","legend":"","description":"","filename":"CoPathsubmission1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8098264/v1/0edafbf3d21de5dcfbda57b8.pdf"},{"id":97229394,"identity":"e3e5341c-bd67-4012-8217-9c129ed06d21","added_by":"auto","created_at":"2025-12-02 09:06:34","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12938,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS2593258T.json","url":"https://assets-eu.researchsquare.com/files/rs-8098264/v1/346c66e97332f402b656ee56.json"},{"id":97251100,"identity":"dae45b4d-eab3-46bf-bd1c-04ad7764e302","added_by":"auto","created_at":"2025-12-02 13:16:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3587170,"visible":true,"origin":"","legend":"Article File","description":"","filename":"CoPathsubmission1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8098264/v1_covered_8c4259c1-83c0-4852-93c5-00fa606389da.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Histopathology Analysis, Pathology Foundation Model, Cancer Diagnosis, Large Language Model, Visual Language Model, Large Reasoning Model","lastPublishedDoi":"10.21203/rs.3.rs-8098264/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8098264/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Advances in AI have introduced several strong models in computational pathology to usher it into the era of multi-modal diagnosis, analysis, and interpretation. However, the current pathology-specific visual language models still lack capacities in making diagnosis with rigorous reasoning paths as well as handling divergent tasks, and thus challenges of building AI Copilots for real scenarios still exist. Here we introduce TeamPath, an AI system powered by reinforcement learning and router-enhanced solutions based on large-scale histopathology multimodal datasets, to work as a virtual assistant for expert-level disease diagnosis, patch-level information summarization, and cross-modality generation to integrate transcriptomic information for the clinical usage. We also collaborate with pathologists from Yale School of Medicine to demonstrate that TeamPath can assist them in working more efficiently by identifying and correcting expert conclusions and reasoning paths. Overall, TeamPath can flexibly choose the best settings according to the needs, and serve as an innovative and reliable system for information communication across different modalities and experts.","manuscriptTitle":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 09:06:29","doi":"10.21203/rs.3.rs-8098264/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1c447e0a-270e-461a-a008-85902551d43c","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":58739106,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":58739107,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":58739108,"name":"Biological sciences/Cancer/Cancer genomics"}],"tags":[],"updatedAt":"2026-04-06T13:31:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 09:06:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8098264","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8098264","identity":"rs-8098264","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}