TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning

2025-02-27

AI Summary

Existing travel planning datasets suffer from high semi-syntheticity, spatiotemporal inconsistency, and missing real-world constraints, severely limiting the practical applicability of LLMs in realistic itinerary generation. To address this, we introduce the first spatiotemporally consistent, constraint-complete travel planning benchmark, integrating real-world public transit schedules, attraction operating hours, activity diversity, and user personas. We propose a novel five-dimensional continuous evaluation framework—including temporal dining coherence, spatial continuity, and persona alignment—overcoming limitations of binary correctness metrics; and design a parameterized meal scheduling mechanism to enhance temporal plausibility. Leveraging multi-source geospatial time-series data and fine-grained user persona modeling, combined with LLM-based generation and rigorous evaluation, our method improves temporal dining coherence from 61% to 80% on 7-day itineraries. The dataset and code are publicly released, establishing a high-fidelity, scalable benchmark for LLM-driven personalized travel planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Constraint Satisfaction and Optimization: Satisfiability

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
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Recent advancements in probing Large Language Models (LLMs) have explored their latent potential as personalized travel planning agents, yet existing benchmarks remain limited in real world applicability. Existing datasets, such as TravelPlanner and TravelPlanner+, suffer from semi synthetic data reliance, spatial inconsistencies, and a lack of key travel constraints, making them inadequate for practical itinerary generation. To address these gaps, we introduce TripCraft, a spatiotemporally coherent travel planning dataset that integrates real world constraints, including public transit schedules, event availability, diverse attraction categories, and user personas for enhanced personalization. To evaluate LLM generated plans beyond existing binary validation methods, we propose five continuous evaluation metrics, namely Temporal Meal Score, Temporal Attraction Score, Spatial Score, Ordering Score, and Persona Score which assess itinerary quality across multiple dimensions. Our parameter informed setting significantly enhances meal scheduling, improving the Temporal Meal Score from 61% to 80% in a 7 day scenario. TripCraft establishes a new benchmark for LLM driven personalized travel planning, offering a more realistic, constraint aware framework for itinerary generation. Dataset and Codebase will be made publicly available upon acceptance.

Problem

• Addresses limitations in existing travel planning datasets.
• Introduces TripCraft for realistic, constraint-aware itinerary generation.
• Proposes continuous evaluation metrics for LLM-generated travel plans.

Innovation

• Integrates real-world constraints for travel planning
• Proposes five continuous evaluation metrics for itineraries
• Enhances meal scheduling with parameter-informed settings