Behavior2Trip：基于用户行为轨迹的个性化旅行规划
Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
浏览论文内容
中文总结 AI 辅助
该研究提出行为感知旅行规划新任务，构建Behavior2Trip基准，提出B2T-Agent智能体，实验显示其在旅行规划任务上表现优于基线，凸显任务挑战性与模型泛化性。
中文摘要 AI 辅助
旅行规划智能体通过对用户个体偏好进行建模，辅助用户生成个性化旅行计划。现有智能体要么依赖用户的明确指令，要么通过多轮澄清来获取用户偏好，但这两种方法均忽略了用户过往行为中蕴含的丰富行为信号——这些信号隐含编码了用户偏好。对主动用户输入的过度依赖增加了交互负担，且限制了计划的个性化程度。为填补这一空白，本文提出了“行为感知旅行规划”新任务，该任务可直接从用户过往行为中推断偏好并生成个性化旅行计划。为推动该任务的研究，本文构建了Behavior2Trip基准，其数据来源于国内最大的在线旅行平台之一，包含11400个实例，每个实例平均对应39.8次用户过往行为，覆盖5个偏好维度的14个属性。本文进一步提出了B2T-Agent，一种基于强化学习的智能体，它利用用户行为轨迹、与外部工具交互以进行符合偏好的检索，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构建的B2T-Agent优于所有基线方法，凸显了该任务的巨大挑战性；此外，经B2T-Agent训练的Qwen3-8B在TravelPlanner基准上的表现也优于GPT-4.1，展现出强大的泛化能力。代码和数据可在指定URL获取。
英文摘要
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
发表机构
- Meituan Inc.（美团公司）
- School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
- Beijing Institute of Technology（北京理工大学）
- University of Edinburgh（爱丁堡大学）
机构由 AI 辅助整理，请以论文原文为准。
