2025/09/08 by Jie Yang, Yang, Jie, Jiajun Chen +17
Engineering · #Artificial Intelligence (cs.AI) #Automotive industry #Autonomous Vehicle Technology and Safety #Code (set theory) #Computation and Language (cs.CL) #Executable #FOS: Computer and information sciences #Function (biology) #Implementation #Inefficiency #Robotics (cs.RO) #State (computer science) #Task (project management) #Vehicular Ad Hoc Networks (VANETs)
paper · pdf · doi:10.48550/arxiv.2509.06736
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/09/08 · openalex created_date 2025/10/11 · openalex updated_date 2026/08/05
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.