Embark Now: User Demand Oriented Framework for Multi-day Urban Travel Itinerary Planning

2026-07-12

AI Summary

This study addresses the challenge of balancing user satisfaction and itinerary feasibility in multi-day urban tourism planning, where a vast number of points of interest (POIs), diverse user preferences, and operational constraints such as opening hours complicate optimal scheduling. To tackle this, the authors propose an end-to-end framework that integrates large language models (LLMs) with an enhanced Greedy Randomized Adaptive Search Procedure (GRASP). This approach leverages LLMs for the first time to dynamically and accurately model complex user preferences, while the improved GRASP enables efficient, preference-aware itinerary optimization. Experiments on real-world datasets from Beijing and Tianjin demonstrate that the proposed framework outperforms baseline methods by 4.52%–11.09% in total itinerary scores, achieves 17.95%–26.07% higher computational efficiency, and delivers up to a 25.55% improvement in overall performance within shorter runtime.

Abstract

In 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 suboptimal methods that require multiple iterations. These outcomes underscore our method's superiority in delivering both enhanced itinerary quality and computational efficiency over existing methodologies.

Problem

• multi-day travel itinerary planning
• user demand
• Points of Interest
• traveler preferences
• urban tourism

Innovation

• Large Language Models
• GRASP algorithm
• multi-day itinerary planning
• user preference modeling
• computational efficiency