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

TL;DR

This paper bridges cognitive neuroscience and AI to enhance autonomous agents' memory systems by synthesizing interdisciplinary insights, analyzing memory mechanisms, benchmarks, security, and future directions.

Contribution

It systematically connects human memory mechanisms with AI memory systems, providing a comprehensive framework and analysis for designing more effective autonomous agents.

Findings

Comparison of biological and artificial memory systems

Review of benchmarks for agent memory evaluation

Discussion on memory security and future research directions

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.