Theory-Informed Generative Agents for Human Mobility Modeling

Theory-Informed Generative Agents for Human Mobility Modeling | 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 Theory-Informed Generative Agents for Human Mobility Modeling Hongru Du, Haoyang Li, Runzhou Liu, Yao Li, Amy Wesolowski, Sen Pei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8902418/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 Human mobility follows robust population-level regularities, yet individual behavior remains highly heterogeneous and context-dependent. The advances of generative agents (large language model (LLM)–driven, persona-conditioned computational agents) offer a promising approach to modeling rich, individualized behavior, but they often lack theoretical grounding and do not readily scale to population-level simulation due to the computational cost of generating decisions for large numbers of agents over long horizons. To reconcile mechanistic understanding with flexible, human-like decision modeling, we introduce a theory-informed mobility agent (TIMA) framework that integrates the physical constraints of mobility theory with the semantic reasoning of LLMs. Mechanistically, the LLM parameterizes the decision tendencies within the physical mobility model process to capture both the scaling laws of aggregate flows and the heterogeneity of individual preferences. Unlike prior LLM agents that are typically evaluated on small, bespoke samples, TIMA enables population-scale simulation while reconstructing key mobility patterns and diverse activity portfolios across multiple U.S. cities in a data-light manner. Beyond pattern reconstruction, we leverage TIMA to investigate mobility-mediated social phenomena. Specifically, we examine how individual choices shape experienced segregation and drive behavioral adaptations in response to external shocks. Using the COVID-19 pandemic as a case study, we demonstrate that the framework naturally captures shifts in segregation and reductions in activity as a function of evolving disease risk and policy constraints. Ultimately, this work illustrates a paradigm for integrating physical theory with generative AI, providing a scalable and flexible foundation for the next generation of policy-relevant behavioral simulation. Scientific community and society/Social sciences/Interdisciplinary studies Health sciences/Diseases/Infectious diseases Social science/Science, technology and society Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Appendix.pdf Theory-Informed Generative Agents for Human Mobility Modeling 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-8902418","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":595773681,"identity":"b90c3e3f-f5e5-4891-aad8-629ad0d86c6d","order_by":0,"name":"Hongru Du","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYFCCBAbDBgYbBjYg8wCDAUSEoJbCBoY0ErV8bGA4jCqCF/AdT364cUbN+cQ+6eMXDxcU2DHws+cY4NUieeaZseGGY7cT2/hyCg7PMEhmkOx5g1+LwY0cNsOHDbeN2Xh4Eg7zGDCDRAhqYf/5sOEcTEs9gz0RWhgMNzYckGPjYT8A1HKYwUCCsF8MDGccSwZq4WEAajnOI3HmWQFeLcAQe2DYU2PHI9/D/vgzz59qOf725A14tQCjDwZ4wO7hwa8cVQv7A8KqR8EoGAWjYEQCAG15R87mWLyRAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-7008-2943","institution":"University of Virginia","correspondingAuthor":true,"prefix":"","firstName":"Hongru","middleName":"","lastName":"Du","suffix":""},{"id":595773682,"identity":"47e594ed-53a8-46ae-b25c-d0aa9b7472f9","order_by":1,"name":"Haoyang Li","email":"","orcid":"https://orcid.org/0009-0002-5598-6236","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Haoyang","middleName":"","lastName":"Li","suffix":""},{"id":595773683,"identity":"47afea82-84f0-46ec-8877-ea1bbbddab2e","order_by":2,"name":"Runzhou Liu","email":"","orcid":"","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Runzhou","middleName":"","lastName":"Liu","suffix":""},{"id":595773684,"identity":"3a27bb0e-862e-4df0-b097-2d7be6b5ec1c","order_by":3,"name":"Yao Li","email":"","orcid":"","institution":"University of North Carolina at Charlotte","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Li","suffix":""},{"id":595773685,"identity":"0c8fd210-8d0b-4726-bd33-5a6695280e6c","order_by":4,"name":"Amy Wesolowski","email":"","orcid":"","institution":"Johns Hopkins Bloomberg School of Public Health","correspondingAuthor":false,"prefix":"","firstName":"Amy","middleName":"","lastName":"Wesolowski","suffix":""},{"id":595773686,"identity":"fbbb677f-6237-43d6-b4ad-1975eb460707","order_by":5,"name":"Sen Pei","email":"","orcid":"https://orcid.org/0000-0002-7072-2995","institution":"Columbia University","correspondingAuthor":false,"prefix":"","firstName":"Sen","middleName":"","lastName":"Pei","suffix":""}],"badges":[],"createdAt":"2026-02-17 15:32:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8902418/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8902418/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106404465,"identity":"97c7140b-d5cb-4746-813e-ff5d5c16c1d3","added_by":"auto","created_at":"2026-04-08 09:16:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3862925,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8902418/v1_covered_c7e3a9fd-0ab7-43b0-ae25-4908f5539304.pdf"},{"id":103425704,"identity":"81ddbeba-abeb-4d97-913e-a5d19d2ef416","added_by":"auto","created_at":"2026-02-25 14:19:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":13293253,"visible":true,"origin":"","legend":"Theory-Informed Generative Agents for Human Mobility Modeling","description":"","filename":"Appendix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8902418/v1/6adeb97a850e1b0d907b984f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Theory-Informed Generative Agents for Human Mobility Modeling","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":"","lastPublishedDoi":"10.21203/rs.3.rs-8902418/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8902418/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Human mobility follows robust population-level regularities, yet individual behavior remains highly heterogeneous and context-dependent. The advances of generative agents (large language model (LLM)–driven, persona-conditioned computational agents) offer a promising approach to modeling rich, individualized behavior, but they often lack theoretical grounding and do not readily scale to population-level simulation due to the computational cost of generating decisions for large numbers of agents over long horizons. To reconcile mechanistic understanding with flexible, human-like decision modeling, we introduce a theory-informed mobility agent (TIMA) framework that integrates the physical constraints of mobility theory with the semantic reasoning of LLMs. Mechanistically, the LLM parameterizes the decision tendencies within the physical mobility model process to capture both the scaling laws of aggregate flows and the heterogeneity of individual preferences. Unlike prior LLM agents that are typically evaluated on small, bespoke samples, TIMA enables population-scale simulation while reconstructing key mobility patterns and diverse activity portfolios across multiple U.S. cities in a data-light manner. Beyond pattern reconstruction, we leverage TIMA to investigate mobility-mediated social phenomena. Specifically, we examine how individual choices shape experienced segregation and drive behavioral adaptations in response to external shocks. Using the COVID-19 pandemic as a case study, we demonstrate that the framework naturally captures shifts in segregation and reductions in activity as a function of evolving disease risk and policy constraints. Ultimately, this work illustrates a paradigm for integrating physical theory with generative AI, providing a scalable and flexible foundation for the next generation of policy-relevant behavioral simulation.","manuscriptTitle":"Theory-Informed Generative Agents for Human Mobility Modeling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-25 14:18:55","doi":"10.21203/rs.3.rs-8902418/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":"1dcfe1bb-5924-4314-8c60-1cc217a5d35d","owner":[],"postedDate":"February 25th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63394142,"name":"Scientific community and society/Social sciences/Interdisciplinary studies"},{"id":63394143,"name":"Health sciences/Diseases/Infectious diseases"},{"id":63394144,"name":"Social science/Science, technology and society"}],"tags":[],"updatedAt":"2026-04-07T15:03:29+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-25 14:18:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8902418","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8902418","identity":"rs-8902418","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}