RETAIL: Towards Real-world Travel Planning for Large Language Models

TL;DR

This paper introduces RETAIL, a comprehensive dataset and a novel multi-agent framework, TGMA, to improve real-world travel planning by addressing implicit queries, environmental factors, and detailed POI integration, significantly advancing the field.

Contribution

The paper presents RETAIL, a new dataset supporting implicit and explicit queries with environmental context, and proposes TGMA, a topic-guided multi-agent framework for enhanced travel planning.

Findings

Existing models achieve only 1.0% pass rate on real-world tasks.

TGMA improves performance to 2.72%, showing promising progress.

RETAIL enables more realistic and detailed travel plan generation.

Abstract

Although large language models have enhanced automated travel planning abilities, current systems remain misaligned with real-world scenarios. First, they assume users provide explicit queries, while in reality requirements are often implicit. Second, existing solutions ignore diverse environmental factors and user preferences, limiting the feasibility of plans. Third, systems can only generate plans with basic POI arrangements, failing to provide all-in-one plans with rich details. To mitigate these challenges, we construct a novel dataset \textbf{RETAIL}, which supports decision-making for implicit queries while covering explicit queries, both with and without revision needs. It also enables environmental awareness to ensure plan feasibility under real-world scenarios, while incorporating detailed POI information for all-in-one travel plans. Furthermore, we propose a topic-guided multi-agent framework, termed TGMA. Our experiments reveal that even the strongest existing model achieves merely a 1.0% pass rate, indicating real-world travel planning remains extremely challenging. In contrast, TGMA demonstrates substantially improved performance 2.72%, offering promising directions for real-world travel planning.