Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks

arXiv:2601.22509v2 Announce Type: replace-cross Abstract: Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each...