iTIMO: An LLM-empowered Synthesis Dataset for Travel Itinerary Modification

2026-01-15

AI Summary

Existing research on itinerary planning primarily focuses on static scenarios, which inadequately supports the dynamic modification of travel plans during trips. This work formalizes, for the first time, the “itinerary editing” task and introduces a synthetic data generation framework grounded in three atomic edit operations—REPLACE, ADD, and DELETE—and three realistic user intents: popularity, spatial proximity, and category diversity. Leveraging large language models (LLMs), the authors construct a high-quality dataset, termed iTIMO. Through a carefully designed hybrid evaluation metric, experiments reveal significant limitations of current LLMs in performing this task, thereby establishing both a foundational dataset and methodological framework to guide future research in dynamic itinerary planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored due to the scarcity of need-to-modify itinerary data. To bridge this gap, we formally define the itinerary modification task and propose a general pipeline to construct the corresponding dataset, namely iTIMO. This pipeline frames the generation of need-to-modify itinerary data as an intent-driven perturbation task. It instructs large language models to perturb real-world itineraries using three operations: REPLACE, ADD, and DELETE. Each perturbation is grounded in three intents: disruptions of popularity, spatial distance, and category diversity. Furthermore, hybrid evaluation metrics are introduced to ensure perturbation effectiveness. We conduct comprehensive benchmarking on iTIMO to analyze the capabilities and limitations of state-of-the-art LLMs. Overall, iTIMO provides a comprehensive testbed for the modification task, and empowers the evolution of traditional travel recommender systems into adaptive frameworks capable of handling dynamic travel needs. Dataset, code and supplementary materials are available at https://github.com/zelo2/iTIMO.

Problem

• itinerary modification
• travel itinerary
• dataset synthesis
• LLM-empowered
• intent-driven perturbation

Innovation

• itinerary modification
• LLM-empowered synthesis
• intent-driven perturbation
• atomic editing operations
• travel itinerary dataset