发表机构
Tech LLC; University of Massachusetts Amherst; University of Virginia（529科技有限责任公司; 马萨诸塞大学阿默斯特分校; 弗吉尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对航空旅行打包易出错问题，提出含符号引擎、偏好学习器和CP - SAT优化器的推理引导学习框架，能生成个性化、合规行李清单，在实验中表现良好，在应用中提升了清单完成量并减少了时间。
AI 中文摘要
航空旅行打包是反复出现且容易出错的：清单必须个性化且具备情境感知能力，同时要在安全规则、物品依赖和行李限制下可行。现有打包助手要么是模板驱动且通用的，要么是推荐驱动但无约束的。我们提出一个有三个阶段的推理引导学习框架：一是生成有明确依赖结构的合规种子清单的符号引擎；二是通过用户添加和删除操作估计包含和优先级效用并减轻生存偏差的两阶段偏好学习器；三是选择紧凑、合规子集的CP - SAT优化器。该架构实例化了一种约束个性化的通用模式。在604个带标签的旅行场景上，符号引擎召回率达99.7%，规则有效性为0.96，梯度提升树和LambdaMART的AUC - ROC为0.943，NDCG@5为0.923，CP - SAT约束满足率达100%。在生产iOS旅行应用FlyEnJoy中部署后，清单完成量翻倍，编辑和完成时间减少。
英文摘要
Packing for air travel is recurring and error-prone: the checklist must be personal and context-aware, yet feasible under safety rules, item dependencies, and luggage limits. Existing packing assistants are template-driven and generic, or recommendation-driven but unconstrained, leaving users to manually patch regulatory and capacity violations. We propose a reasoning-guided learning framework with three stages: (1) a symbolic engine that generates a regulation-aware seed checklist with explicit dependency structure, (2) a two-stage preference learner that estimates inclusion and priority utilities from user add and remove actions while mitigating survivorship bias, and (3) a CP-SAT optimizer that selects a compact, compliant subset. The architecture instantiates a general pattern for constrained personalization, applicable wherever hard feasibility coexists with sparse preference signals. On 604 labeled trip scenarios, comprising 29K inclusion labels and 343K pairwise comparisons, the symbolic engine attains 99.7% recall and 0.96 rubric validity, compared with 0.78 to 0.81 for frontier LLMs. Gradient-boosted trees and LambdaMART reach an AUC-ROC of 0.943 and an NDCG@5 of 0.923. CP-SAT attains 100% constraint satisfaction, compared with 28% for greedy selection and 10% for random selection. Deployment in FlyEnJoy, a production iOS travel app, doubled checklist completions and reduced editing and completion time.
