提出首个汽车智能交互综合环境，提升车载代理执行效率
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
- 构建包含30模块250接口的实时可执行环境
- 状态驱动方法比传统调用准确率更高、延迟更低
- 适合自动驾驶交互与智能座舱研究者使用
智能汽车座舱对API代理提出独特挑战，需协调高度耦合的子系统，其复杂度远超常规任务环境。传统函数调用（FC）方式无状态，需多次探索性调用才能建立环境认知，导致效率低下且容错能力差。我们提出VehicleWorld，首个面向汽车领域的综合性环境，包含30个模块、250个API和680个属性，具备完全可执行实现，支持代理执行时实时获取状态信息。该环境可精准评估车辆代理在多样化复杂场景下的行为表现。系统分析发现，直接状态预测优于函数调用。基于此，我们提出状态驱动函数调用（SFC），通过显式维护系统状态并实现直接状态转移以达成目标条件。实验表明，SFC显著优于传统FC方法，在执行准确率和延迟方面均有提升。所有代码已开源至GitHub：https://github.com/OpenMOSS/VehicleWorld。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。