WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents· WorldAuditBench：多模态代理的3D世界审计
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, traversable walls, or objects inconsistent with the surrounding scene. Multimodal AI systems, including vision-language models (VLMs) and vision-language-action models (VLAs), have shown potential for automating this task. However, 3D world auditing is complex, requiring the close coupling of two distinct capabilities: action, to navigate the 3D world and search for anomalies systematically and efficiently; and visual reasoning, to understand the environment and identify anomalies from multimodal observations. It remains largely unexplored whether multimodal agents can effective
利用多模态代理进行3D世界审计，自动检测环境异常。
- 核心方法
- 结合了VLMs和VLAs的能力，实现3D世界的系统性和效率性导航及异常检测。
- 适合谁读
- 研究者
- 要解决的问题
- 如何在复杂的3D世界中有效地检测异常，如悬浮物体、可穿透的墙等。
- 关键实验
- 未提供
- 主要贡献
- 提出了WorldAuditBench框架，推动了多模态代理在3D世界审计任务上的研究进展。
- 意义与局限
- 该研究为提高3D环境的准确性和可信度提供了新工具，但方法的有效性和普适性需进一步验证。