Julian, JackKoh, Yun SingBifet, Albert2026-08-242026-08-242025Julian, J., Koh, Y. S., & Bifet, A. (2025). Building adaptive knowledge bases for evolving continual learning models. npj Artificial Intelligence, 1(1), Article 26. https://doi.org/10.1038/s44387-025-00028-43005-1460https://hdl.handle.net/10289/18581Continual learning addresses catastrophic forgetting and knowledge transfer when learning from task streams. Dynamic architectures have introduced task-specific components like adapters layered over fixed pre-trained backbones. However, identifying the task of a new input remains a core challenge, leading to task-agnostic and dynamic detection methods. Existing approaches often overlook the reuse of previously learned adapters, missing opportunities for efficient forward and backwards transfer. We propose Continual Adapter-Based Learning (CABLE), a reinforcement learning framework that computes gradient similarity between new examples and past tasks. This similarity score drives a policy that assigns existing adapters when beneficial, rewarding improved performance and reducing reliance on newly initialised parameters. CABLE adopts a dynamic adapter routing strategy without assuming prior task labels. Evaluations on image classification and time series forecasting show that CABLE mitigates catastrophic forgetting and promotes efficient knowledge transfer across tasks.enAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/computer scienceJournal Article10.1038/s44387-025-00028-43005-146046 Information and Computing Sciences4602 Artificial Intelligence4611 Machine Learning