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

2024-11-01

arXiv.org

AI Summary

Current artificial intelligence (AI) long-term memory (LTM) systems lack a unified theoretical foundation and interpretable mechanisms. Method: This project establishes, for the first time, a systematic cross-modal cognitive mapping between human brain LTM and AI LTM; proposes the Self-Adaptive Long-term Memory (SALM) cognitive architecture, unifying theoretical modeling with system design; and integrates cognitive modeling, brain-inspired mechanism analysis, and architectural design to construct the first comprehensive AI LTM framework covering mechanisms, formal modeling, and applications. Contribution/Results: Key outcomes include the first panoramic survey of AI LTM, the SALM theoretical framework, a clearly defined technological evolution roadmap, and multiple application-oriented deployment pathways across diverse scenarios. Collectively, these advances provide foundational support for next-generation LTM-driven AI systems.

Technology Category

Cognitive Modeling & Cognitive Systems: Agent ArchitecturesMachine Learning: Large Multimodal Models (LMMs)Multiagent Systems: Agent/AI Theories and Architectures

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Large language models for searchSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Artificial Intelligence
• Long-term Memory
• Theoretical Framework

Innovation

• Self-Adaptive Long-term Memory
• Cognitive Architecture
• Artificial Intelligence Memory Enhancement