Levels of AI Agents: from Rules to Large Language Models

TL;DR

This paper proposes a hierarchical classification of AI agents inspired by autonomous driving levels, ranging from simple tools to complex, emotionally capable multi-agent systems, highlighting the evolution of AI capabilities.

Contribution

It introduces a novel 6-level framework categorizing AI agents based on their utilities and capabilities, from basic tools to emotionally intelligent multi-agent systems.

Findings

Defines 6 levels of AI agents with increasing complexity.

Provides a structured perspective on AI development stages.

Highlights the integration of emotion and collaboration in advanced AI agents.

Abstract

AI agents are defined as artificial entities to perceive the environment, make decisions and take actions. Inspired by the 6 levels of autonomous driving by Society of Automotive Engineers, the AI agents are also categorized based on utilities and strongness, as the following levels: L0, no AI, with tools taking into account perception plus actions; L1, using rule-based AI; L2, making rule-based AI replaced by IL/RL-based AI, with additional reasoning & decision making; L3, applying LLM-based AI instead of IL/RL-based AI, additionally setting up memory & reflection; L4, based on L3, facilitating autonomous learning & generalization; L5, based on L4, appending personality of emotion and character and collaborative behavior with multi-agents.