Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Jie, Chen, Jiajun, Yin, Zhangyue, Chen, Shuo, Wang, Yuxin, Guo, Yiran, Li, Yuan, Zheng, Yining, Huang, Xuanjing, Qiu, Xipeng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.06736
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911142895419392
author Yang, Jie
Chen, Jiajun
Yin, Zhangyue
Chen, Shuo
Wang, Yuxin
Guo, Yiran
Li, Yuan
Zheng, Yining
Huang, Xuanjing
Qiu, Xipeng
author_facet Yang, Jie
Chen, Jiajun
Yin, Zhangyue
Chen, Shuo
Wang, Yuxin
Guo, Yiran
Li, Yuan
Zheng, Yining
Huang, Xuanjing
Qiu, Xipeng
contents 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 https://github.com/OpenMOSS/VehicleWorld.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
Yang, Jie
Chen, Jiajun
Yin, Zhangyue
Chen, Shuo
Wang, Yuxin
Guo, Yiran
Li, Yuan
Zheng, Yining
Huang, Xuanjing
Qiu, Xipeng
Artificial Intelligence
Computation and Language
Robotics
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 https://github.com/OpenMOSS/VehicleWorld.
title VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
topic Artificial Intelligence
Computation and Language
Robotics
url https://arxiv.org/abs/2509.06736