VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction

Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu


Abstract
Intelligent vehicle cockpits present unique challenges for API Agents, requiring coordination across tightly-coupled subsystems that exceed typical task environments’ complexity. Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery. We introduce VehicleWorld, the first comprehensive environment for the automotive domain, featuring 30 modules, 250 APIs, and 680 properties with fully executable implementations that provide real-time state information during agent execution. This environment enables precise evaluation of vehicle agent behaviors across diverse, challenging scenarios. Through systematic analysis, we discovered that direct state prediction outperforms function calling for environmental control. Building on this insight, we propose State-based Function Call (SFC), a novel approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions. Experimental results demonstrate that SFC significantly outperforms traditional FC approaches, achieving superior execution accuracy and reduced latency. We have made all implementation code publicly available on GitHub.
Anthology ID:
2025.findings-emnlp.23
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
403–442
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.23/
DOI:
Bibkey:
Cite (ACL):
Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, and Xipeng Qiu. 2025. VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 403–442, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (Yang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.23.pdf
Checklist:
 2025.findings-emnlp.23.checklist.pdf