Shalil Ahmadi, Shokouh (Purdue University), Li, Lingxi (Purdue University)

Large Language Models for Autonomous Driving: A Review of Technical Challenges, Datasets, and Simulation Environments

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

Large Language Models (LLMs) have emerged as transformative tools in artificial intelligence, primarily known for their capabilities in natural language understanding and generation. Recently, their potential to enhance autonomous driving (AD) systems has garnered growing interest. By introducing interpretability, human-like reasoning, and flexible interaction mechanisms, LLMs offer promising solutions to long-standing challenges in the AD domain, including the lack of transparency, common-sense decision-making, and intuitive human-machine interaction. However, their integration into AD systems presents new concerns related to data quality, prompt engineering, safety, and reliability in real-time environments. This paper provides a comprehensive overview of the current landscape of LLMs in autonomous driving, outlining the main contributions, existing challenges, benchmark datasets, and simulation tools. We also highlight future research directions to bridge the gap between natural language intelligence and autonomous vehicle safety and performance.