Lune

EMNLP Findings2025

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 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  2. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  3. WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the EnvironmentHao Tang, Darren Key, Kevin EllisNeurIPS 2024 · 123 citations
  4. SciAgent: Tool-augmented Language Models for Scientific ReasoningYubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu et al.EMNLP 2024 · 13 citations
  5. Search-o1: Agentic Search-Enhanced Large Reasoning ModelsXiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang et al.EMNLP 2025 · 12 citations

Related papers

  1. Automating a Complete Software Test Process Using LLMs: An Automotive Case StudyShuai Wang, Yinan Yu, Robert Feldt, Dhasarathy ParthasarathyICSE 2025 · 4 citations
  2. C-World: A Computer Use Agent Environment CreatorZiqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang et al.ACL 2026 · 1 citation
  3. Towards General Agentic Intelligence via Environment ScalingRunnan Fang, Shihao Cai, Baixuan Li, Jialong Wu et al.ACL Findings 2026 · 1 citation
  4. MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented EnvironmentsQuyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao et al.ACL 2026 · 38 citations
  5. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous AgentsChristopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines