Abstract
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:
- Symbolic Engine: Generates a regulation-aware seed checklist with explicit dependency structure.
- Two-Stage Preference Learner: Estimates inclusion and priority utilities from user add and remove actions while mitigating survivorship bias.
- CP-SAT Optimizer: 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 achieves 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.
Blogger's Review: This framework effectively combines reasoning and learning to address personalized needs under complex constraints, demonstrating significant real-world effectiveness and great potential for broader applications.