RETAIL: Towards Real-world Travel Planning for Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916911114092544 |
|---|---|
| author | Deng, Bin Feng, Yizhe Liu, Zeming Wei, Qing Zhu, Xiangrong Chen, Shuai Guo, Yuanfang Wang, Yunhong |
| author_facet | Deng, Bin Feng, Yizhe Liu, Zeming Wei, Qing Zhu, Xiangrong Chen, Shuai Guo, Yuanfang Wang, Yunhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15335 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RETAIL: Towards Real-world Travel Planning for Large Language Models Deng, Bin Feng, Yizhe Liu, Zeming Wei, Qing Zhu, Xiangrong Chen, Shuai Guo, Yuanfang Wang, Yunhong Artificial Intelligence 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. |
| title | RETAIL: Towards Real-world Travel Planning for Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15335 |