通过闭环世界建模实现视频化身中的主动智能
Active Intelligence in Video Avatars via Closed-loop World Modeling
把视频生成模型当作可交互环境，用闭环的观察-思考-行动-反思循环和结果校验来修正生成漂移，为长时程视频生成中的状态一致性问题提供了一个可复用的推理-生成耦合框架。
原文依据 a closed-loop OTAR cycle (Observe-Think-Act-Reflect) that maintains robust state tracking under generative uncertainty
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前的视频化身生成方法在身份保持与运动对齐方面表现出色，但缺乏真正的能动性——它们无法通过自适应的环境交互来自主追求长期目标。为解决这一问题，我们提出了 L-IVA（长时程交互式视觉化身），这是一个用于评估随机生成环境中目标导向规划的任务与基准，以及 ORCA（在线推理与认知架构），这是首个在视频化身中实现主动智能的框架。ORCA 通过两项关键创新体现内部世界模型（IWM）能力：(1) 闭环 OTAR 循环（观察-思考-行动-反思），通过持续将预测结果与实际生成结果进行校验，在生成不确定性下维持稳健的状态跟踪；(2) 分层双系统架构，其中系统 2 借助状态预测进行策略推理，系统 1 将抽象计划转化为精确的、针对具体模型的动作描述。通过将化身控制建模为 POMDP 并实现带有结果校验的连续信念更新，ORCA 能够在开放域场景中自主完成多步任务。大量实验表明，ORCA 在任务成功率和行为连贯性上显著优于开环与无反思基线，验证了我们受 IWM 启发的设计能够推动视频化身智能从被动动画迈向主动的、目标导向的行为。
英文原文摘要 1466 字符
Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency--they cannot autonomously pursue long-term goals through adaptive environmental interaction. We address this by introducing L-IVA (Long-horizon Interactive Visual Avatar), a task and benchmark for evaluating goal-directed planning in stochastic generative environments, and ORCA (Online Reasoning and Cognitive Architecture), the first framework enabling active intelligence in video avatars. ORCA embodies Internal World Model (IWM) capabilities through two key innovations: (1) a closed-loop OTAR cycle (Observe-Think-Act-Reflect) that maintains robust state tracking under generative uncertainty by continuously verifying predicted outcomes against actual generations, and (2) a hierarchical dual-system architecture where System 2 performs strategic reasoning with state prediction while System 1 translates abstract plans into precise, model-specific action captions. By formulating avatar control as a POMDP and implementing continuous belief updating with outcome verification, ORCA enables autonomous multi-step task completion in open-domain scenarios. Extensive experiments demonstrate that ORCA significantly outperforms open-loop and non-reflective baselines in task success rate and behavioral coherence, validating our IWM-inspired design for advancing video avatar intelligence from passive animation to active, goal-oriented behavior.