The AI Hippocampus: How Far are We From Human Memory?
Zixia Jia, Jiaqi Li, Yipeng Kang, Yuxuan Wang, Tong Wu, Quansen Wang, Xiaobo Wang, Shuyi Zhang, Junzhe Shen, Qing Li, Siyuan Qi, Yitao Liang, Di He, Zilong Zheng, Song-Chun Zhu

TL;DR
This survey explores how memory mechanisms in large language models and multi-modal systems enhance reasoning, adaptability, and personalization, categorizing memory types and discussing recent advances, challenges, and future directions.
Contribution
It provides a comprehensive taxonomy of memory paradigms in LLMs and MLLMs, integrating recent research on implicit, explicit, and agentic memory frameworks.
Findings
Implicit memory enables knowledge embedding within model parameters.
Explicit memory allows external, dynamic knowledge retrieval.
Agentic memory supports long-term planning and multi-agent collaboration.
Abstract
Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of continual learning and personalized inference, the incorporation of memory mechanisms has emerged as a central theme in their architectural and functional evolution. This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms. Specifically, the survey delineates three primary memory frameworks. Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers, encompassing their capacity for memorization, associative retrieval, and contextual reasoning. Recent work has…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Memory and Neural Mechanisms · Action Observation and Synchronization
