# FastHarness: A Robot Execution Framework That Schedules LLM Review Using Task Experience

- Source: CVer · 微信公众号
- Published: 2026-10-27T12:29:04.000Z
- RoboHot: https://robohot.news/en/items/urgrz0ljv4qic19t1d7dxistf
- Original: https://mp.weixin.qq.com/s?__biz=MzUxNjcxMjQxNg==&mid=2247644042&idx=2&sn=d10f64d85fb6da2bf8ceb7cab3af6fe8&chksm=f8cbec49aae0377ac907cfaab74aa12efb73d6a5b6d04c5933fe495c0aa6d9845e8b56472441&scene=126&sessionid=1793109624#rd

## Summary

FastHarness is an experience-driven robot execution framework that uses π0.5 to generate actions and GPT-6 Astra to review and correct them, adjusting the review interval according to task stage and past review results. Across four simulated manipulation tasks in RoboDojo, it achieved an average success rate of 97.19%, higher than the 80% reported for π0.5 + GPT-6 Astra in the GPT-as-Policy report.