Position: Modular Memory is the Key to Continual Learning Agents
Toyota Motor Europe · Universität Bremen · University of Florence · Microsoft Research · University of Pisa · Mila · CITEC, Bielefeld University · Arsenale Bioyards · KU Leuven · University of Rochester · University of Texas at San Antonio · Nankai University · Stony Brook University · Mila/University of Montreal · University of Tübingen · University of Trento · University of Groningen · Tsinghua University · Computer Vision Center Barcelona · Seoul National University · University of Bremen
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Foundation models have transformed machine learning through large-scale pretraining, massive parameterization, 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, 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, thereby mitigating catastrophic forgetting and charting a practical roadmap toward continually learning agents.