# ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience

arXiv: https://arxiv.org/abs/2508.08101 · HTML: https://mlsanity.com/paper/2508.08101/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 119 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 7 of 7)

- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Emotionally-Aware Chatbots: A Survey](https://mlsanity.com/paper/1906.09774/) (2019)
- [Affective Conversational Agents: Understanding Expectations and Personal Influences](https://mlsanity.com/paper/2310.12459/) (2023)
- [Towards Proactive Interactions for In-Vehicle Conversational Assistants Utilizing Large Language Models](https://mlsanity.com/paper/2403.09135/) (2024)
- [What is "Intelligent" in Intelligent User Interfaces? A Meta-Analysis of 25 Years of IUI](https://mlsanity.com/paper/2003.03158/) (2020)
- [Affective Automotive User Interfaces -- Reviewing the State of Emotion Regulation in the Car](https://mlsanity.com/paper/2003.13731/) (2020)
- [Lessons from Oz: Design Guidelines for Automotive Conversational User Interfaces](https://mlsanity.com/paper/1907.11179/) (2019)

## Built on by (most cited first, 3 of 3)

- [Visual and Cognitive Demands of a Large Language Model-Powered In-vehicle Conversational Agent](https://mlsanity.com/paper/2601.15034/) (2026)
- [CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits](https://mlsanity.com/paper/2608.01805/) (2026)
- [Multimodal Drivers' Emotion Recognition and Safety-Oriented Intervention for Intelligent Transportation Systems](https://mlsanity.com/paper/2608.06378/) (2026)

## Abstract (arXiv)

Studies on in-vehicle conversational agents have traditionally relied on pre-scripted prompts or limited voice commands, constraining natural driver-agent interaction. To resolve this issue, the present study explored the potential of a ChatGPT-based in-vehicle agent capable of carrying continuous, multi-turn dialogues. Forty drivers participated in our experiment using a motion-based driving simulator, comparing three conditions (No agent, Pre-scripted agent, and ChatGPT-based agent) as a within-subjects variable. Results showed that the ChatGPT-based agent condition led to more stable driving performance across multiple metrics. Participants demonstrated lower variability in longitudinal acceleration, lateral acceleration, and lane deviation compared to the other two conditions. In subjective evaluations, the ChatGPT-based agent also received significantly higher ratings in competence, animacy, affective trust, and preference compared to the Pre-scripted agent. Our thematic analysis of driver-agent conversations revealed diverse interaction patterns in topics, including driving assistance/questions, entertainment requests, and anthropomorphic interactions. Our results highlight the potential of LLM-powered in-vehicle conversational agents to enhance driving safety and user experience through natural, context-rich interactions.