AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents

2025-12-29

AI Summary

This study addresses the gap between cognitive neuroscience and large language model (LLM)-driven autonomous agents in memory modeling—specifically, the lack of an interdisciplinary unifying framework, unsystematic lifecycle management of memory (encoding, storage, retrieval, forgetting), and inadequate security mechanisms. Methodologically, we propose the first biologically inspired–artificial memory unified analytical paradigm, integrating memory definitions, taxonomies, core mechanisms, and multimodal skill acquisition pathways. Our approach synergizes neural scientific principles, LLM architecture analysis, standardized memory benchmarking, and adversarial security modeling to construct a structured knowledge graph covering memory taxonomy, closed-loop memory management, and security evaluation. The contribution is a theoretically grounded yet engineering-practical paradigm and actionable guidelines for designing memory systems in embodied intelligent agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research on autonomous agents has increasingly focused on designing efficient memory workflows by drawing on cognitive neuroscience. However, constrained by interdisciplinary barriers, existing works struggle to assimilate the essence of human memory mechanisms. To bridge this gap, we systematically synthesizes interdisciplinary knowledge of memory, connecting insights from cognitive neuroscience with LLM-driven agents. Specifically, we first elucidate the definition and function of memory along a progressive trajectory from cognitive neuroscience through LLMs to agents. We then provide a comparative analysis of memory taxonomy, storage mechanisms, and the complete management lifecycle from both biological and artificial perspectives. Subsequently, we review the mainstream benchmarks for evaluating agent memory. Additionally, we explore memory security from dual perspectives of attack and defense. Finally, we envision future research directions, with a focus on multimodal memory systems and skill acquisition.

Problem

• Bridging cognitive neuroscience with AI memory design
• Analyzing memory taxonomy and lifecycle across disciplines
• Exploring memory security and future multimodal systems

Innovation

• Integrating cognitive neuroscience insights with LLM-driven agents
• Comparing biological and artificial memory taxonomies and lifecycles
• Exploring memory security from attack and defense perspectives