TravelAgent: An AI Assistant for Personalized Travel Planning

TL;DR

TravelAgent is an AI-powered travel planning system utilizing large language models to generate personalized, comprehensive, and practical itineraries in dynamic scenarios, outperforming rule-based and LLM-based existing methods.

Contribution

The paper introduces TravelAgent, a novel LLM-based travel planning system with four modules that effectively addresses rationality, comprehensiveness, and personalization in dynamic travel scenarios.

Findings

TravelAgent achieves high effectiveness in personalized recommendations.

The system outperforms existing methods in key travel planning criteria.

Evaluation confirms the accuracy and practicality of generated itineraries.

Abstract

As global tourism expands and artificial intelligence technology advances, intelligent travel planning services have emerged as a significant research focus. Within dynamic real-world travel scenarios with multi-dimensional constraints, services that support users in automatically creating practical and customized travel itineraries must address three key objectives: Rationality, Comprehensiveness, and Personalization. However, existing systems with rule-based combinations or LLM-based planning methods struggle to fully satisfy these criteria. To overcome the challenges, we introduce TravelAgent, a travel planning system powered by large language models (LLMs) designed to provide reasonable, comprehensive, and personalized travel itineraries grounded in dynamic scenarios. TravelAgent comprises four modules: Tool-usage, Recommendation, Planning, and Memory Module. We evaluate TravelAgent's performance with human and simulated users, demonstrating its overall effectiveness in three criteria and confirming the accuracy of personalized recommendations.