构建真实旅行规划数据集与多智能体框架，提升大模型实际应用能力
RETAIL: Towards Real-world Travel Planning for Large Language Models
- 提出主题引导的多智能体框架TGMA，处理隐式需求与环境因素
- 在RETAIL数据集上，新方法通过率2.72%，远超旧模型的1.0%
- 适合关注真实场景智能规划、旅行应用落地的研究者与开发者
尽管大语言模型提升了自动化旅行规划能力，现有系统仍与现实场景脱节。首先，假设用户给出明确查询，而现实中需求常为隐式；其次，忽略环境因素与用户偏好，影响计划可行性；第三，仅生成基础景点安排，缺乏完整细节。为此，我们构建了新数据集RETAIL，支持隐式与显式查询（含修订需求），具备环境感知能力，并包含丰富景点信息，实现一体化行程规划。同时提出主题引导的多智能体框架TGMA。实验表明，最强现有模型通过率仅为1.0%，而TGMA达2.72%，显著提升，为真实世界旅行规划提供可行方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。