Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances

TL;DR

This survey reviews recent advances in multi-agent autonomous driving systems that incorporate large language models to improve collaboration, decision-making, and communication, addressing key challenges in perception and computational efficiency.

Contribution

It categorizes existing LLM-based multi-agent ADS methods, discusses agent-human interactions, and summarizes applications, datasets, and challenges for future research.

Findings

LLMs enhance inter-agent communication in ADSs.

Multi-agent systems improve safety and efficiency.

Current challenges include perception limitations and high computational costs.

Abstract

Autonomous Driving Systems (ADSs) are revolutionizing transportation by reducing human intervention, improving operational efficiency, and enhancing safety. Large Language Models (LLMs) have been integrated into ADSs to support high-level decision-making through their powerful reasoning, instruction-following, and communication abilities. However, LLM-based single-agent ADSs face three major challenges: limited perception, insufficient collaboration, and high computational demands. To address these issues, recent advances in LLM-based multi-agent ADSs leverage language-driven communication and coordination to enhance inter-agent collaboration. This paper provides a frontier survey of this emerging intersection between NLP and multi-agent ADSs. We begin with a background introduction to related concepts, followed by a categorization of existing LLM-based methods based on different agent interaction modes. We then discuss agent-human interactions in scenarios where LLM-based agents engage with humans. Finally, we summarize key applications, datasets, and challenges to support future research.