arXiv 2603.017612026-06-17cs.LGcs.AI

Position: 模块化记忆是持续学习智能体的关键

Position: Modular Memory is the Key to Continual Learning Agents

University of Bremen（不莱梅大学）；Seoul National University（首尔国立大学）；Computer Vision Center Barcelona（巴塞罗那计算机视觉中心）；University of Florence（佛罗伦萨大学）；Microsoft Research（微软研究院）；HEC Montreal, Mila--Quebec AI Institute, Canada CIFAR AI Chair（蒙特利尔HEC学院、魁北克人工智能研究所、加拿大CIFAR人工智能 chair）；Bielefeld University（比勒海姆大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Rochester（罗切斯特大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Nankai University（南开大学）；LUISS University（卢西亚诺大学）；Stony Brook University（石溪大学）；University of Tübingen（图宾根大学）；University of Trento, FBK（特伦托大学，FBK）；Tsinghua University（清华大学）；University of Groningen（Groningen大学）

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, Barbara Hammer, Tyler L. Hayes, Timm Hess, Christopher Kan… 展开作者

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

备注：: ICML 2026 Position Track Spotlight. This work stems from discussions held at the Dagstuhl seminar on Continual Learning in the Era of Foundation Models (October 2025)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出通过模块化记忆结合权重内学习与上下文学习，解决持续学习中的灾难性遗忘问题，实现大规模持续适应。

摘要：

基础模型通过大规模预训练和增加测试时计算已经改变了机器学习。尽管在多个领域超越了人类表现，这些模型在持续运行、经验积累和个性化方面仍然存在根本性限制，而这些能力是自适应智能的核心。虽然持续学习研究长期以来一直瞄准这些目标，但其历史上专注于权重内学习（IWL），即更新单个模型的参数以吸收新知识，导致灾难性遗忘成为一个持续挑战。我们的立场是，通过设计模块化记忆，结合权重内学习（IWL）和新出现的上下文学习（ICL）的优势，是实现大规模持续适应的缺失环节。我们概述了一个以模块化记忆为中心的架构的概念框架，该架构利用ICL进行快速适应和知识积累，利用IWL对模型能力进行稳定更新，为持续学习智能体绘制了一条实用的路线图。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。