Flexible Routing via Uncertainty Decomposition

ArXi:2605.07805v1 Announce Type: new A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a expensive oracle (such as a large pretrained model or human expert), an approach known as model routing. In this work we present a new uncertainty-aware router that (1) avoids unnecessary oracle calls on inherently ambiguous queries, and (2) adapts dynamically to different loss functions and cost parameters through simple hyperparameter changes, without re.