# Continual Model Routing in Evolving Model Hubs Source: [Continual Model Routing in Evolving Model Hubs]() Collection index: [llms.txt]() Data updated: 2026-05-29T05:00:12.873Z Authors: Jack Bell, Giacomo Carf\\\`i, Gerlando Gramaglia, Vincenzo Lomonaco Published: 2026-05-27T15:00:45.000Z ## Abstract AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands of experts and continually updating routing mechanisms as new models and tasks are introduced. In this paper, we formalise this setting as Continual Model Routing (CMR) and propose CMRBench, a new large-scale benchmark simulating realistic hub expansion and including over 2,000 candidate models. Finally, we introduce CARvE, a contrastive embedding approach for efficient continual model routing via checkpoint-based anchoring and structured replay. Extensive empirical results and ablations show that CARvE significantly outperforms zero-shot retrieval, fine-tuning, and adapter-merging baselines in model, family, and domain-level accuracy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Continual Model Routing on CMRBench v1 (test)](): Continual Model Routing; CMRBench v1 (test); D-Acc: 85.7. ## Original sources and implementation [Original paper]() [PDF]()