Human-inspired Perspectives: A Survey on AI Long-term Memory

TL;DR

This survey systematically reviews AI long-term memory mechanisms, draws parallels with human memory, introduces a new theoretical framework called SALM, and discusses future research directions and applications.

Contribution

It provides a comprehensive mapping between human and AI memory systems, and proposes the SALM framework to guide future development of AI long-term memory.

Findings

Established a mapping between human and AI memory mechanisms

Proposed the SALM framework for AI long-term memory

Outlined future directions and applications for AI memory systems

Abstract

With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.