360CityArena：面向具身智能体的真实虚拟城市导航基准

摘要

我们提出360CityArena，一个用于在由360度视频构建的照片级逼真环境中评估具身智能体城市探索能力的基准。现有的户外基准要么缺乏足够的逼真度，要么缺乏足够的复杂度，导致与现实城市环境之间存在相当大的差距。360CityArena基于日本东京秋叶原地区的真实感重建，使用覆盖85条街道的602段360度视频，并由175项人工精心设计的任务组成。它涵盖三类任务：环境理解、路径推理和空间推理，覆盖城市探索所需的基本能力，如定位、地标搜索、路径规划和关系空间推理，从而能够在真实城市场景中进行全面评估。我们使用基于LMM的最先进智能体进行的评估表明，即使是最强的模型Gemini 2.5 Flash，其表现也远低于人类水平（人类：77.3%对Gemini 2.5 Flash：17.1%），这揭示了城市规模的具身导航与推理中仍然存在的重大挑战。360CityArena为照片级逼真的城区环境中的导航与空间推理提供了一个必要且具有挑战性的测试平台。

English

We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos. Existing outdoor benchmarks either lack sufficient photorealism or complexity, resulting in a considerable gap from real-world urban environments. 360CityArena is built on a realistic reconstruction of the Akihabara district in Tokyo, Japan, using 602 360-degree video segments covering 85 streets, and consists of 175 meticulously human-crafted tasks. It encompasses three task categories: Environment Understanding, Path Reasoning, and Spatial Reasoning, covering fundamental abilities required for urban exploration, such as localization, landmark search, path planning, and relational spatial reasoning, thereby enabling comprehensive evaluation in realistic urban scenes. Our evaluation using state-of-the-art LMM-based agents shows that even the strongest model, Gemini 2.5 Flash, performs far below human level (human: 77.3% vs. Gemini 2.5 Flash: 17.1%), revealing substantial challenges that remain in city-scale embodied navigation and reasoning. 360CityArena provides a necessary and challenging testbed for photorealistic urban-district navigation and spatial reasoning.