论文/arXiv 2610.03476·26 天前

MobiAgent：用于长程移动操作的双循环递归策略自我改进

MobiAgent面向长程移动操作，用双循环框架结合原子技能规划与自主学习，并在仿真和真实任务上验证。

AI 整理

• 本体 SDK 与控制
• 感知与导航
• 具身模型

原文链接：MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation（arXiv 2610.03476 · 发布日期：2026-10-02）

MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation

MobiAgent面向长程移动操作，用双循环框架结合原子技能规划与自主学习，并在仿真和真实任务上验证。

核心要点

• 长程移动操作面临执行误差累积，以及移动与机械臂控制的容量干扰。
• 内循环用VLM进行滚动规划和视觉反思，动态组合原子技能以恢复错误。
• 外循环自主分割、验证和聚类部署轨迹，无需人工标注地持续微调技能库。
• 在BEHAVIOR-1K上较π_{0.5}-TA高22.5个百分点，并提升RoboCasa和Astribot S1成功率。

验证范围与局限：验证范围为RoboCasa、BEHAVIOR-1K和真实世界任务。

英文摘要 (Abstract)

Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and arm control. While recent Vision-Language-Action models excel at short-horizon tasks, they lack the hierarchical reasoning required for multi-stage objectives. Furthermore, existing hierarchical agents suffer from rigid sub-task mapping, inflexible replanning, and a lack of continuous learning. To address these limitations, we introduce MobiAgent, a dual-loop agentic framework that bridges robust deployment execution and recursive policy self-improvement. During deployment, the Inner Loop decouples high-level reasoning from low-level control through highly composable atomic skills. It employs Vision-Language models for receding-horizon planning and visual reflection, dynamically composing skills to ensure robust error recovery. These skills are executed by specialized flow-matching experts that share a unified VLM backbone, maximizing reusability while mitigating capacity interference. Concurrently, the Outer Loop drives automated lifelong learning by autonomously segmenting and verifying deployment rollouts, clustering them to discover atomic skills, and continuously fine-tuning the skill library without human annotations. Evaluations on RoboCasa, BEHAVIOR-1K, and real-world tasks demonstrate the effectiveness of MobiAgent. It outperforms $π_{0.5}$-TA by 22.5 percentage points on BEHAVIOR-1K and enables robust recovery from execution failures. Through autonomous data recycling, success improves from 7.50% to 27.50% on RoboCasa and from 32.5% to 57.5% on Astribot S1.

作者：Chenzhi Liu, Yue Zhang, Jiehong Lin, Jianan Wang, Bo Wang, Zhongrui Wang, Xiaojuan Qi

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.03476：MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation访问 2026-10-21