VehicleArena：用于多智能体驾驶的真实城市环境

中文摘要 AI 辅助

现实世界中的具身智能体通常在共享的物理环境中追求各自独立的目标，其行为可能会改变其他智能体所面临的条件。然而，现有的基准通常假设共享目标或明确规定的交互协议，使得这种涌现的物理耦合未被充分探索。我们引入了VehicleArena，一个用于研究在动态共享世界中独立运行的智能体的3D城市驾驶基准。在VehicleArena中，由LLM控制的智能体必须在应对复杂交通的同时满足不断变化的乘客请求，并且每个智能体的驾驶决策都可能重塑周围智能体的交通流、延误、风险以及后续观察。该基准提供了112个评估任务，涵盖单智能体和多智能体驾驶。在九个评估模型中，单智能体任务中的最高到达率仅为65.0%，多智能体任务中的最高到达率仅为65.6%，而较高的乘客请求或座舱评分并不能可靠地转化为成功的行程完成。此外，在匹配的多智能体运行中，每个测试的焦点策略相对于模拟器的原生交通控制器都降低了周围车辆的到达率，揭示了超出焦点车辆本身的可测量的外部性。

英文摘要

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.

发表机构

• Fudan University（复旦大学）
• Shanghai Innovation Institute（上海创新研究院）

机构由 AI 辅助整理，请以论文原文为准。