用真实评价生成更符合用户感受的旅行计划，避免只看数据忽略体验。
TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning
- 拆分行程为住宿、交通、餐饮等专用代理，协同生成个性化路线。
- 引入10万条真实评价数据，提升计划对舒适度、拥挤度等体验因素的考量。
- 提出新评估指标RGPA，用AI判断计划是否真正贴近人的旅行感受。
旅行行程生成需平衡时空约束与用户偏好。现有基于大模型的规划器主要依赖结构化属性和预设旅行者画像，但真实出行决策常受评论影响，而评论揭示了舒适度、安全性、服务质量、氛围、人流状况及隐性风险等结构数据库中缺失的体验因素。因此，融合评论信息对生成真实、以用户为中心的行程至关重要。我们提出TRIPPULSE，一个基于评论的多智能体旅行规划框架。不同于单一规划器（易出现上下文和推理瓶颈），TRIPPULSE将行程生成分解为专门代理（各自处理局部上下文）——涵盖住宿、交通、餐饮、景点与活动，并通过全局协调器与调度机制确保时间与预算可行性。我们还扩充了TRIPCRAFT数据集至10万+真实评论，提出评审式画像对齐（RGPA）——一种以LLM为裁判的评估指标，用于衡量行程与以人为本旅行体验的一致性。在多种行程时长和多样私有/开源模型上的实验表明，TRIPPULSE在保持强约束满足的同时，生成了更具个性化和体验基础的行程。
原文摘要 · Abstract (English)
Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on structured attributes and pre- defined traveler personas, but real travel deci- sions are often shaped by reviews that reveal experiential factors such as comfort, safety, ser- vice quality, ambiance, crowding, and hidden risks absent from structured databases. Incor- porating such review information is therefore critical to realistic, user-centric itinerary gen- eration. We propose TRIPPULSE1, a multi- agent framework for review-grounded travel planning. Instead of relying on a monolithic planner (and face context and reasoning bot- tlenecks), TRIPPULSE2 decomposes itinerary generation into specialized agents (each op- erating over localized contexts) for accom- modations, transportation, meals, attractions, and events, coordinated through a global or- chestrator with scheduling mechanisms that enforce temporal and budget feasibility. We augment TRIPCRAFT with 100K+ real-world reviews and introduce Review-Grounded Per- sona Alignment (RGPA), an LLM-as-a-Judge metric for evaluating alignment with human- centric travel experiences. Experiments across multiple trip durations and diverse proprietary and open-source models show that TRIPPULSE maintains strong constraint satisfaction while generating more personalized and experien- tially grounded itineraries.
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。