RETAIL: Towards Real-world Travel Planning for Large Language Models
This addresses the misalignment of automated travel planning systems with real-world user needs, though it is incremental as it builds on existing methods with a new dataset and framework.
The paper tackles the problem of real-world travel planning with large language models, which currently fail to handle implicit queries, environmental factors, and detailed plans, by introducing a dataset RETAIL and a topic-guided multi-agent framework TGMA, resulting in improved performance from 1.0% to 2.72% pass rate.
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.