Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modular Memory is the Key to Continual Learning Agents

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, Barbara Hammer, Tyler L. Hayes, Timm Hess, Christopher Kanan, Dhireesha Kudithipudi, Xialei Liu, Vincenzo Lomonaco, Jorge Mendez-Mendez, Darshan Patil, Ameya Prabhu, Elisa Ricci, Tinne Tuytelaars, Gido M. van de Ven, Liyuan Wang, Joost van de Weijer, Jonghyun Choi, Martin Mundt, Rahaf Aljundi

TL;DR

This work outlines 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.

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.

Modular Memory is the Key to Continual Learning Agents

TL;DR

This work outlines 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.

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.
Paper Structure (16 sections, 1 figure, 1 table)

This paper contains 16 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Memory across Soft-, Hard- & Wetware
  3. Early Use of Memory in Continual Learning
  4. Memory in Modern Large-scale Models
  5. Memory in Humans and Computers
  6. A Modular Memory Framework for Continual Learning Agents
  7. Main System Components
  8. System Operation
  9. Designing a Modular Memory
  10. Memory Representations
  11. Memory Structure and Functions
  12. Challenges and Opportunities
  13. Opportunities for Memory-Centric Agents
  14. Challenging Application Domains
  15. Alternative Views
  16. ...and 1 more sections

Figures (1)

  • Figure 1: An illustration of the role of memory in unlocking continual learning through the construction of distinct modules. The framework comprises (1) a core model for perception and reasoning, (2) a working memory module for temporarily storing information relevant to the current interaction round, and (3) a long-term memory module that accumulates extracted experiences, facts, and observations. Knowledge stored in long-term memory is selectively retrieved into working memory and consolidated into the core model, steadily improving its capabilities.