An In-depth Survey of Large Language Model-based Artificial Intelligence Agents

TL;DR

This survey comprehensively compares large language model-based AI agents with traditional ones, highlighting their advantages, analyzing core components, and proposing a novel memory classification scheme to guide future research.

Contribution

The paper provides an in-depth comparison of LLM-based and traditional AI agents, introduces a novel memory classification scheme, and offers future research directions.

Findings

LLM-based agents excel in natural language processing and reasoning.

A new classification scheme for AI agent memory is proposed.

Insights into core components like planning, memory, and tool use.

Abstract

Due to the powerful capabilities demonstrated by large language model (LLM), there has been a recent surge in efforts to integrate them with AI agents to enhance their performance. In this paper, we have explored the core differences and characteristics between LLM-based AI agents and traditional AI agents. Specifically, we first compare the fundamental characteristics of these two types of agents, clarifying the significant advantages of LLM-based agents in handling natural language, knowledge storage, and reasoning capabilities. Subsequently, we conducted an in-depth analysis of the key components of AI agents, including planning, memory, and tool use. Particularly, for the crucial component of memory, this paper introduced an innovative classification scheme, not only departing from traditional classification methods but also providing a fresh perspective on the design of an AI agent's memory system. We firmly believe that in-depth research and understanding of these core components will lay a solid foundation for the future advancement of AI agent technology. At the end of the paper, we provide directional suggestions for further research in this field, with the hope of offering valuable insights to scholars and researchers in the field.