[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85994-en":3,"doc-seo-85994-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85994,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Embark Now User Demand Oriented Framework for Multi-day Urban Travel Itinerary Planning","Large urban areas make multi-day travel itinerary planning difficult because POI abundance, heterogeneous user preferences, and spatiotemporal constraints like opening hours increase both uncertainty and search complexity. This work proposes a user-demand oriented framework that uses Large Language Models (LLMs) to capture requirements with precision and an enhanced GRASP preference-aware planner to produce feasible itineraries. Experiments on Beijing and Tianjin datasets show at least 4.52% and 11.09% higher average itinerary scores across 5,040 cases, alongside end-to-end metric gains and improved time efficiency versus suboptimal multi-iteration approaches.","arXiv :2607 . 1065 1v 1 [ cs .AI] 12 Jul 2026  \nEmbark Now: User Demand Oriented Framework for Multi-day Urban Travel Itinerary Planning  \nRongbo Qi 1 , Yaqi Zhang 1 , Shijun Yan2 , Xuemeng Liu3 , Xiangrui Cai 1 , Chunyao Song 1*  \n1* College of Computer Science, Nankai University, Tianjin, 300350,  \nTianjin, China.  \n2 Jiangxi Normal University, Nanchang, 330022, Jiangxi, China.  \n3 College of Software, Nankai University, Tianjin, 300350, Tianjin, China.  \n*Corresponding author(s). E-mail(s): [chunyao.song@nankai.edu.cn](chunyao.song@nankai.edu.cn) ; Contributing authors: [rongbo.qi@mail.nankai.edu.cn](rongbo.qi@mail.nankai.edu.cn) ;  \n[yaqi.zhang@mail.nankai.edu.cn](yaqi.zhang@mail.nankai.edu.cn) ; [shijunyan@jxnu.edu.cn](shijunyan@jxnu.edu.cn) ;  \n[xuemeng.liu@mail.nankai.edu.cn](xuemeng.liu@mail.nankai.edu.cn) ; [caixr@nankai.edu.cn](caixr@nankai.edu.cn) ;  \nAbstract  \nIn large urban areas, planning multi-day travel itineraries is challenging due to the abundance of Points of Interest (POIs), diverse user preferences, and constraints such as opening hours. Effective solutions must dynamically accommodate diverse traveler requirements while optimizing for satisfaction and feasibility within limited computation time. This paper addresses these challenges through introducing an innovative framework that integrates Large Language Models (LLMs) to dynamically capture user requirements with precision and flexibility, and an enhanced Greedy Randomized Adaptive Search Procedure (GRASP) algorithm as a well-suited preference-aware planner to generate feasible multi-day itineraries. The effectiveness of our integrated approach is demonstrated through extensive experiments on two real-world urban datasets from Beijing and Tianjin. Our framework significantly outperforms state-of-the-art (SOTA) methods, improving the average total itinerary score by at least 4.52% and 11 .09% across 5,040 user cases with diverse preferences in the two datasets. Furthermore, through end-to-end algorithmic enhancements, it achieves notable average improvements of 17.95% and 26.07% in the computed metrics, while also delivering substantial gains in time efficiency – realizing average performance increases of 4.64% and 25.55% within shorter computation times compared to  \n1  \nsuboptimal methods that require multiple iterations. These outcomes underscore our method’s superiority in delivering both enhanced itinerary quality and computational efficiency over existing methodologies.  \nKeywords: travel itinerary planning, personalized travel plans, multi-day urban  \ntravel plans, heuristic planning algorithms  \n1 Introduction  \nWith advancements in transportation and tourism, many travelers are inclined to explore unfamiliar cities (Halder et al. , 2024) . Despite the abundance of detailed POI (Points of Interest) data offered by various travel assistant apps, including attractions, dining options, and accommodations, as well as the curated travel itineraries provided by professional travel agencies, users still confront significant challenges when it comes to swiftly crafting a comprehensive and personalized multi-day travel plan in a large city for themselves or their families in an unfamiliar city (Orabi et al. , 2025; Yhee et al. , 2023) . These challenges stem not only from the large solution space, but also from diverse user preferences (e.g., fast-paced vs. slow-paced), and from spatiotemporal constraints (e.g., opening hours, travel times, and daily time budgets) . We refer to this setting as the Multi-day Urban Travel Itinerary Planning (MUTIP) problem. Hence, the development of automated algorithms that are capable of accurately discerning diverse and user-specific preferences becomes imperative for crafting tailored itineraries that cater to individual needs.  \nConventionally, this obstacle is studied under the Tourist Trip Design Problem (TTDP) (Liao & Zheng, 2018; Vansteenwegen et al. , 2011), a complex issue that is often decomposed into two distin","cbCaio6ZyDnCTcGE","https://ap.wps.com/l/cbCaio6ZyDnCTcGE","pdf",3272558,2,1,37,"English","en",105,"# Introduction\n# Related Work and Motivation\n# Challenges and Proposed Solutions","[{\"question\":\"What is the MUTIP problem addressed in the document?\",\"answer\":\"It defines Multi-day Urban Travel Itinerary Planning (MUTIP) as the task of quickly generating a comprehensive, personalized multi-day plan in a large city under diverse preferences and spatiotemporal constraints such as opening hours and daily time budgets.\"},{\"question\":\"How does the proposed framework use LLMs in itinerary planning?\",\"answer\":\"The framework integrates Large Language Models to dynamically capture user requirements, enabling a preference-aware planning process that adapts to different traveler demands more precisely and flexibly.\"},{\"question\":\"Why is an enhanced GRASP algorithm included alongside LLMs?\",\"answer\":\"LLM-only planning may fail to satisfy concrete spatiotemporal constraints or avoid infeasible POIs in multi-day settings, so the preference-aware enhanced GRASP planner is used to generate feasible itineraries efficiently.\"}]",1784207654,93,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"embark-now-user-demand-oriented-framework-for-multi-day-urban-travel-itinerary-planning","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/embark-now-user-demand-oriented-framework-for-multi-day-urban-travel-itinerary-planning/85994/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the MUTIP problem addressed in the document?","Question",{"text":75,"@type":76},"It defines Multi-day Urban Travel Itinerary Planning (MUTIP) as the task of quickly generating a comprehensive, personalized multi-day plan in a large city under diverse preferences and spatiotemporal constraints such as opening hours and daily time budgets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework use LLMs in itinerary planning?",{"text":80,"@type":76},"The framework integrates Large Language Models to dynamically capture user requirements, enabling a preference-aware planning process that adapts to different traveler demands more precisely and flexibly.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is an enhanced GRASP algorithm included alongside LLMs?",{"text":84,"@type":76},"LLM-only planning may fail to satisfy concrete spatiotemporal constraints or avoid infeasible POIs in multi-day settings, so the preference-aware enhanced GRASP planner is used to generate feasible itineraries efficiently.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]