Learning to Defer: A Survey

Learning to defer (L2D) enables AI systems to choose between autonomous prediction and deferral to experts. This survey consolidates the fast-growing literature through a four-branch taxonomy: methodological frameworks; optimization and theory; task generalizations; and real-world adaptations. We outline contrasts between score-based and predictor–rejector formulations; one-stage, two-stage, and post-hoc training; unify surrogate losses with theoretical guarantees; and synthesize extensions to regression, multi-task prediction, top-$k$ committees, sequential settings, and causal pipelines. Practical considerations include limited annotations, dynamic expert pools, workload/budget control, fairness, interpretability, robustness, and uncertainty handling, concluding with open challenges for reliable human–AI decision systems.

Note: This is the preprint version of a manuscript currently under review. It has not undergone peer review.