arXiv AI· Wenrui Bao, Xinxin Liu, Bingxin Xu, Yuzhang Shang·· 11 小时前评分60
Recursive Video In-Context Learning for Agentic Robot
摘要
原文摘录（自动中文摘要暂不可用）：Recursive Video In-Context Learning for Agentic Robot 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 los
推荐理由
自动中文摘要尚未通过校验，请核对原文与完整来源。
本站只提供摘要与原文入口。完整内容请阅读原文。
来源：arXiv AI · arxiv.org