Modular Memory is the Key to Continual Learning Agents

TL;DR

This paper proposes a modular memory architecture that combines in-weight learning and in-context learning to enable continual adaptation and knowledge accumulation in foundation models, addressing persistent challenges like catastrophic forgetting.

Contribution

It introduces a conceptual framework for modular memory-centric architectures that integrate ICL and IWL for scalable continual learning.

Findings

Framework outlines how modular memory enables rapid adaptation.

Combines ICL and IWL for stable, continual learning.

Charts a practical roadmap for continually learning agents.

Abstract

Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning (IWL), i.e., updating a single model's parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale. We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, charting a practical roadmap toward continually learning agents.