发表机构
University of Central Florida; University of Southern California（中佛罗里达大学; 南加州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出RV-ICL，一种无需训练的递归视频上下文学习方法，将演示视频组织为层级结构供智能体按需访问，在LIBERO基准上将成功率提升至96.5%和95.8%。
AI 中文摘要
编排冻结的视觉-语言-动作（VLA）策略的LLM智能体通过文本记忆在多个回合中提升表现，文本记忆记录了智能体做了什么，但未记录任务如何完成。演示视频展示了任务如何完成，但难以适配智能体的上下文。完整视频拖慢每一轮交互，固定关键帧丢失了决定抓取是否成功的接触细节，而智能体的需求从规划时的任务结构转变为每个接触点周围的帧。我们提出递归视频上下文学习（RV-ICL），一种无需训练的方法，将演示转化为智能体导航的层级结构，而非接收的提示。该层级结构由演示的子事件（如抓取和释放）构建。其层级逐渐细化，从整个任务的关键帧到阶段、时刻和短视频片段，并通过只读工具暴露。智能体在规划前读取粗粒度层级。执行过程中，每当步骤需要更多细节时，它重新进入层级，仅加载当前子目标的片段。每个任务只需一个演示即可。基于RPent，RV-ICL在LIBERO-PRO上将成功率从92.6%提升至96.5%，在LIBERO-Plus上从86.7%提升至95.8%。
英文摘要
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fits poorly into an agent's context. The full video slows every turn, fixed keyframes lose the contact detail that decides whether a grasp holds, and what the agent needs shifts from the task's structure while planning to the frames around each contact. We introduce Recursive Video In-Context Learning (RV-ICL), a training-free method that turns a demonstration into a hierarchy the agent navigates rather than a prompt it receives. The hierarchy is built from the sub-events of the demonstration, such as grasps and releases. Its levels grow finer, from keyframes of the whole task to phases, moments and short clips, and are exposed through read-only tools. The agent reads the coarse levels before planning. During execution it re-enters the hierarchy whenever a step needs more detail and loads only the clip of its current sub-goal. One demonstration per task is enough. Built on RPent, RV-ICL raises success from 92.6% to 96.5% on LIBERO-PRO and from 86.7% to 95.8% on LIBERO-Plus.
