Digital human generation has been studied for decades and supports a wide range of real-world applications. However, most existing systems are passively animated, relying on privileged state or scripted control, which limits scalability to novel environments. We instead ask: how can digital humans actively behave using only visual observations and specified goals in novel scenes? Achieving this would enable populating any 3D environments with digital humans at scale that exhibit spontaneous, natural, goal-directed behaviors. To this end, we introduce Visually-grounded Humanoid Agents, a coupled two-layer (world-agent) paradigm that replicates humans at multiple levels: they look, perceive, reason, and behave like real people in real-world 3D scenes. The World Layer reconstructs semantically rich 3D Gaussian scenes from real-world videos via an occlusion-aware pipeline and accommodates animatable Gaussian-based human avatars. The Agent Layer transforms these avatars into autonomous humanoid agents, equipping them with first-person RGB-D perception and enabling them to perform accurate, embodied planning with spatial awareness and iterative reasoning, which is then executed at the low level as full-body actions to drive their behaviors in the scene. We further introduce a benchmark to evaluate humanoid-scene interaction in diverse reconstructed environments. Experiments show our agents achieve robust autonomous behavior, yielding higher task success rates and fewer collisions than ablations and state-of-the-art planning methods. This work enables active digital human population and advances human-centric embodied AI. Data, code, and models will be open-sourced.

翻译：数字人生成技术已被研究数十年，并支撑着广泛的现实应用。然而，现有系统大多采用被动动画方式，依赖特权状态或脚本控制，限制了其在陌生环境中的可扩展性。我们提出一个相反的问题：数字人能否仅凭视觉观察和指定目标在陌生场景中主动行动？实现这一目标将使得在任意三维环境中大规模部署具备自发、自然、目标导向行为的数字人成为可能。为此，我们提出视觉驱动的类人智能体——一种耦合的双层（世界-智能体）范式，在多个层面模拟人类：它们像真实人类一样在三维场景中进行观察、感知、推理和行动。世界层通过遮挡感知管道从真实世界视频中重建语义丰富的三维高斯场景，并支持可动画化的高斯人体化身。智能体层将这些化身转化为自主类人智能体，赋予其第一人称RGB-D感知能力，使其能够基于空间感知和迭代推理进行精确的具身规划，随后通过低层级的全身动作驱动其在场景中的行为。我们还引入了一个基准测试，用于在多样化重建环境中评估人-场景交互。实验表明，我们的智能体展现出稳健的自主行为，在任务成功率和碰撞次数上均优于消融实验与当前最优规划方法。该项工作实现了主动数字人生成，推动了以人为中心的具身人工智能发展。相关数据、代码和模型将开源。