CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems

ArXi:2604.23022v1 Announce Type: cross Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly ed generator-item pairs.