SAGE: 适用于具身人工智能的可扩展代理3D场景生成
SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
AI总结：
SAGE通过代理框架生成可扩展的3D环境，用于具身人工智能的策略训练和泛化能力提升。
摘要：
现实世界数据收集对于具身代理仍然成本高昂且不安全，亟需可扩展、真实且适用于模拟器的3D环境。然而，现有的场景生成系统往往依赖于基于规则或任务特定的流程，导致产生伪影和物理无效的场景。我们提出了SAGE，一个代理框架，给定用户指定的具身任务（例如
英文摘要：
Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines, yielding artifacts and physically invalid scenes. We present SAGE, an agentic framework that, given a user-specified embodied task (e.g., "pick up a bowl and place it on the table"), understands the intent and automatically generates simulation-ready environments at scale. The agent couples multiple generators for layout and object composition with critics that evaluate semantic plausibility, visual realism, and physical stability. Through iterative reasoning and adaptive tool selection, it self-refines the scenes until meeting user intent and physical validity. The resulting environments are realistic, diverse, and directly deployable in modern simulators for policy training. Policies trained purely on this data exhibit clear scaling trends and generalize to unseen objects and layouts, demonstrating the promise of simulation-driven scaling for embodied AI. Code, demos, and the SAGE-10k dataset can be found on the project page here: https://research.nvidia.com/labs/dir/sage/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
