Abstract
Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions faced by others. Existing benchmarks, however, typically assume shared goals or explicitly prescribed interaction protocols, leaving such emergent physical coupling underexplored. We introduce VehicleArena, a 3D urban-driving benchmark for studying independently operating agents in a dynamic shared world. In VehicleArena, LLM-controlled agents must fulfill evolving passenger requests while navigating complex traffic, and each agent's driving decisions can reshape traffic flow, delays, risks, and subsequent observations for surrounding agents. The benchmark provides 112 evaluation tasks spanning single-agent and multi-agent driving. Across nine evaluated models, the highest arrival rates reach only 65.0% on single-agent tasks and 65.6% on multi-agent tasks, while strong passenger-request or cabin scores do not reliably translate into successful trip completion. Moreover, in matched multi-agent runs, every tested focal policy reduces the arrival rate of surrounding vehicles relative to the simulator's native traffic controller, revealing measurable externalities beyond the focal vehicle itself.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yang, J., Chen, J., Zhou, J., Huang, M., Zheng, Y., Wang, Y., & Qiu, X. (2026). VehicleArena: A Realistic Urban Environment for Multi-Agent Driving. https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving
MLA 9
Yang, Jie, et al. "VehicleArena: A Realistic Urban Environment for Multi-Agent Driving." https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving.
Chicago (author–date)
Yang, Jie, Jiajun Chen, Jiazheng Zhou, Mianqiu Huang, Yining Zheng, Yuxin Wang, and Xipeng Qiu. 2026. "VehicleArena: A Realistic Urban Environment for Multi-Agent Driving." https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving.
Harvard
Yang, J., Chen, J., Zhou, J., Huang, M., Zheng, Y., Wang, Y. and Qiu, X. (2026) 'VehicleArena: A Realistic Urban Environment for Multi-Agent Driving', Available at: https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving.
Vancouver
Yang J, Chen J, Zhou J, Huang M, Zheng Y, Wang Y, et al. VehicleArena: A Realistic Urban Environment for Multi-Agent Driving. https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving
IEEE
J. Yang, J. Chen, J. Zhou, M. Huang, Y. Zheng, Y. Wang, and X. Qiu, "VehicleArena: A Realistic Urban Environment for Multi-Agent Driving," https://omanscience.com/en/articles/vehiclearena-a-realistic-urban-environment-for-multi-agent-driving.