Beyond Forgetting: Toward Mechanistically Grounded Continual Learning

摘要

Continual learning (CL) is a prerequisite for autonomous intelligence. Despite decades of progress, the field has operated largely without a mechanistic account of \emph{where} and \emph{why} forgetting occurs, treating it as a monolithic phenomenon to be suppressed rather than a structured process to be understood. We argue that three recent shifts are collectively redefining the field: (1) a mechanistic turn that localizes forgetting to specific computational circuits; (2) the emergence of foundation models that change the problem entirely; and (3) the imperative to move beyond task-bounded protocols toward genuinely autonomous, boundary-free learning. Grounded in Complementary Learning Systems (CLS) theory, this work identifies fast and slow learning pathways inside large language models, characterizes the structural geometry of forgetting, and constructs deployable CL pipelines with biologically motivated signatures. These directions chart a path toward autonomous learning systems that regulate their own consolidation.