Large Language Model-Augmented Metaheuristics for Itinerary Planning

Large Language Model-Augmented Metaheuristics for Itinerary Planning | 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 Large Language Model-Augmented Metaheuristics for Itinerary Planning Qingcheng Xu, Yang Li, Dongdong Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6756215/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract The increasing demand for tourism highlights the significance of itinerary planning as a key problem in path optimization. Although population-based metaheuristic algorithms have shown promising performance on this problem, they typically start from scratch without prior knowledge and rely on the optimization of a predefined objective function. This approach can be inefficient and may overlook popular points of interest (POIs), depending on the problem formulation. In this paper, we propose a Large Language Model (LLM)-augmented metaheuristic optimization framework to more effectively address the itinerary planning problem. The proposed method first leverages the extensive internal knowledge of an LLM to intelligently select tourist attractions based on user preferences. These selections are then integrated into a discrete Particle Swarm Optimization (PSO) algorithm to optimize the travel itinerary. During the optimization process, if the generated plans deviate from realistic constraints, the LLM dynamically adjusts the selection of POIs. Finally, the LLM integrates the optimized path and time allocation to generate a comprehensive itinerary. A case study conducted in Nanjing, Jiangsu Province, China, compares the proposed approach with a conventional PSO method and an LLM-only planning strategy. Experimental results demonstrate the superiority and practical value of the proposed LLM-augmented optimization framework. Physical sciences/Engineering Physical sciences/Mathematics and computing/Computational science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 03 Jul, 2025 Reviews received at journal 02 Jul, 2025 Reviews received at journal 22 Jun, 2025 Reviewers agreed at journal 17 Jun, 2025 Reviewers agreed at journal 16 Jun, 2025 Reviewers invited by journal 16 Jun, 2025 Editor assigned by journal 13 Jun, 2025 Editor invited by journal 10 Jun, 2025 Submission checks completed at journal 09 Jun, 2025 First submitted to journal 27 May, 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-6756215","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":472681989,"identity":"ac9d1e78-1495-4df9-b32b-6e94dc710438","order_by":0,"name":"Qingcheng Xu","email":"","orcid":"","institution":"Nanjing Polytechnic Institute","correspondingAuthor":false,"prefix":"","firstName":"Qingcheng","middleName":"","lastName":"Xu","suffix":""},{"id":472681994,"identity":"9d3246b5-2d32-40cc-b1c2-0f78d37febfa","order_by":1,"name":"Yang Li","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Li","suffix":""},{"id":472681995,"identity":"e891e159-90b9-4c38-81fd-a019a93945e6","order_by":2,"name":"Dongdong Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYFCCBMMHCRU1clAeM1FajA0+nDlmTJIWM8mZbcyJDURrkW9P3iDNw8aW3j8j95gEQ4V1YgP72QN4tTD2PCsw5uGRyZ1xIy9NguFMemIDT14CXi3MEjkGyTwSbLkbpHPMJBjbDic2SPAY4NXCBtRymMeAOd0ArOUfEVp4JHIMG2ckMCdAtDQQoUWC51kxw4cDxwxn3H9jbJFwLN24jScHvxZgiG3/kfivRp6/54zhjQ811rL97Gfwa0EFCSDfkaB+FIyCUTAKRgEOAADuLT+yeDA71AAAAABJRU5ErkJggg==","orcid":"","institution":"China West Normal University","correspondingAuthor":true,"prefix":"","firstName":"Dongdong","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-05-27 06:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6756215/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6756215/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84925124,"identity":"e180fab6-38f4-4dec-9fb0-9671c3ead876","added_by":"auto","created_at":"2025-06-18 21:42:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1566594,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6756215/v1_covered_0815905b-54eb-4830-ad39-b6ca95c6dcb6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Large Language Model-Augmented Metaheuristics for Itinerary Planning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6756215/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6756215/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The increasing demand for tourism highlights the significance of itinerary planning as a key problem in path optimization. Although population-based metaheuristic algorithms have shown promising performance on this problem, they typically start from scratch without prior knowledge and rely on the optimization of a predefined objective function. This approach can be inefficient and may overlook popular points of interest (POIs), depending on the problem formulation. In this paper, we propose a Large Language Model (LLM)-augmented metaheuristic optimization framework to more effectively address the itinerary planning problem. The proposed method first leverages the extensive internal knowledge of an LLM to intelligently select tourist attractions based on user preferences. These selections are then integrated into a discrete Particle Swarm Optimization (PSO) algorithm to optimize the travel itinerary. During the optimization process, if the generated plans deviate from realistic constraints, the LLM dynamically adjusts the selection of POIs. Finally, the LLM integrates the optimized path and time allocation to generate a comprehensive itinerary. A case study conducted in Nanjing, Jiangsu Province, China, compares the proposed approach with a conventional PSO method and an LLM-only planning strategy. Experimental results demonstrate the superiority and practical value of the proposed LLM-augmented optimization framework.","manuscriptTitle":"Large Language Model-Augmented Metaheuristics for Itinerary Planning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-18 21:34:07","doi":"10.21203/rs.3.rs-6756215/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-03T17:30:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-02T20:38:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-22T09:25:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"17912914832893202460112557483630645801","date":"2025-06-17T16:51:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"176538906462956385335308114182460050151","date":"2025-06-17T01:53:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-16T20:02:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-13T17:08:17+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-10T16:10:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-09T11:48:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-27T06:48:19+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a48e33d3-1e24-4f90-9d35-6015256b678f","owner":[],"postedDate":"June 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":50199662,"name":"Physical sciences/Engineering"},{"id":50199663,"name":"Physical sciences/Mathematics and computing/Computational science"}],"tags":[],"updatedAt":"2026-01-27T05:39:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-18 21:34:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6756215","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6756215","identity":"rs-6756215","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}