MILES-Rec：从移动行为推断隐式意图的跨域 POI 推荐
原标题：MILES-Rec: Uncovering Implicit Intents from Mobility Behaviors for Cross-Domain POI Recommendation
AI 摘要
论文提出 MILES-Rec 跨域 POI 推荐框架，从地图应用中的移动行为（搜索、路线、导航等）推断用户隐含的服务意图，并将其表达为按优先级排序的自然语言查询。方法上先用渐进式推理示范学习情境理解、意图扩展与查询排序，再引入意图对齐的组相对策略优化，以用户后续交互作为奖励，并采用两级信用分配协调单条查询质量与整份查询列表的覆盖度。作者基于大规模地图平台真实交互日志构建 MILES-Bench，实验显示其在 POI 检索效用和服务、语义对齐上优于通用 LLM 与专用推荐基线。
正文节选
MILES-Rec: Uncovering Implicit Intents from Mobility Behaviors for Cross-Domain POI Recommendation Abstract. Map applications bridge everyday mobility with local services, creating opportunities to recommend places by uncovering users’ implicit intents. However, utility-driven map interactions provide only indirect and incomplete evidence of consumption demands, making it challenging to infer personalized service needs from observed behaviors. We propose MILES-Rec, a cross-domain POI recommendat