通过用户历史行为推断偏好，实现更省力的个性化旅行规划
Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
- 从用户过往行为轨迹中挖掘隐含偏好，无需反复提问
- 构建1.14万条真实数据的Behavior2Trip基准，平均39.8条行为记录
- 提出B2T-Agent模型，结合记忆模块与工具调用，效果超越GPT-4.1
旅行规划代理通过建模用户个人偏好来生成个性化行程。现有方法依赖显式指令或多轮澄清以获取偏好，但忽略了用户历史行为中蕴含的丰富隐性信号。这种对主动输入的过度依赖增加了交互负担，限制了个性化程度。为此，我们提出新任务——行为感知旅行规划，直接从过往行为推断用户偏好并生成行程。为推动该任务研究，我们构建了来自中国最大在线旅游平台之一的Behavior2Trip基准，包含11,400个实例，每个实例平均涵盖39.8条跨5个偏好维度、14个属性的历史行为。我们进一步提出B2T-Agent，一种基于强化学习的代理，利用用户行为轨迹，调用外部工具进行偏好对齐检索，并维护内部记忆模块。在Behavior2Trip上的实验显示，GPT-4.1在最难任务上的全约束通过率仅为0.5%，而基于Qwen3-8B的B2T-Agent优于所有基线，凸显该任务的挑战性。此外，使用B2T-Agent训练的Qwen3-8B在TravelPlanner基准上也优于GPT-4.1，表明其强泛化能力。代码与数据已开源。
原文摘要 · Abstract (English)
Travel planning agents assist users in generating personalized travel plans by modeling their individual preferences. Existing agents either rely on explicit user instructions or engage in multi-turn clarification to elicit user preferences. However, both approaches overlook the rich behavioral signals latent in users' past behaviors, which implicitly encode their preferences. This over-reliance on active user input increases interaction burden and limits plan personalization. To bridge this gap, we introduce a new task, Behavior-Aware Travel Planning, which infers user preferences directly from past behaviors and generates personalized travel plans. To facilitate research on this task, we introduce Behavior2Trip, a benchmark constructed from one of the largest Chinese online travel platforms, comprising 11,400 instances. Each instance represents an average of 39.8 past user behaviors spanning 14 attributes across 5 preference dimensions. We further propose B2T-Agent, a reinforcement learning-based agent that leverages user behavior trajectories, interacts with external tools for preference-aligned retrieval, and maintains an internal memory module. Experiments on Behavior2Trip show that GPT-4.1 achieves a full-constraint pass rate of only 0.5\% on the hardest tasks, while B2T-Agent built upon Qwen3-8B outperforms all baselines, highlighting the substantial challenge of this task. Moreover, Qwen3-8B trained with B2T-Agent also outperforms GPT-4.1 on the TravelPlanner benchmark, demonstrating strong generalization. Code and data are available at https://github.com/BUAA-IRIP-LLM/Behavior2Trip
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。