Winter Is Over for Continual Learning: From Continual Representation Learning to Continual Learning Agents

Continual Learning (CL) gained prominence with the rise of deep architectures, and then entered a winter as Large Language Models (LLMs) gave the impression that learning over time was no longer needed. We argue that this winter was not a failure but, in fact, a necessary transition. Intelligence cannot be separated from the evolving time in which an agent lives and acts, and the arrival of agentic systems makes CL return to its proper place: not the narrow question of how representations are formed, but the principle by which agents organise their knowledge as its environment changes. We call these systems Continual Learning Agents, designed from the start to adapt continually and consolidate knowledge over time. In this work, we follow the path from the early ideas about machines that learn over time, through the era of deep CL, towards an holistic view in which continual learning and agent design can no longer be held apart, and in which the hard problems of Artificial Intelligence (AI) and those of CL are seen to converge.