# RoboCoach: Using World Models to Locate Weak Subtasks and Improve Long-Horizon Task Success Through Targeted Teaching

- Source: 机器之心 · 微信公众号
- Published: 2026-10-26T04:15:00.000Z
- RoboHot: https://robohot.news/en/items/uelp8709s5ce6jbjkkm0uy0yv
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651070117&idx=2&sn=50db3b4e73608e6f97eb228ba0a62274&chksm=857b67dac9d7287150fffcf2ccb10bf5693041170fdd891b41d75a40dbbc09059447a5c36ce5&scene=126&sessionid=1793022368#rd

## Summary

Zhang Changshui and Cui Sen's team at Tsinghua University propose RoboCoach, an embodied intelligence system that uses the world model CoachWorld to run closed-loop trials of long-horizon tasks in imagination, identify the first weak subtask that times out, and request targeted human teaching for it, updating only the corresponding skill expert. Under a fixed demonstration budget, the success rate rises from 13.3% to 75.0% on Franka and from 40.0% to 83.8% on AgileX, while the uniform collection baseline reaches only 30.0% and 47.5%, respectively. On four unseen new task routes, the average success rate is 35.0%, compared with 0% for the shared-policy baseline.

## Why it matters

The paper presents a complete experiment on using a world model to locate weak subtasks and improve success rates through targeted teaching; its approach to data budget allocation may be a useful reference.