# Harvard, Nvidia and others propose RAX: robot agent online exploration, leading by 37.4 points on average across five benchmarks

- Source: CVer · 微信公众号
- Published: 2026-10-29T14:02:05.000Z
- RoboHot: https://robohot.news/en/items/zjw61ojibrejvie0dgmwf58fh
- Original: https://mp.weixin.qq.com/s?__biz=MzUxNjcxMjQxNg==&mid=2247644193&idx=3&sn=2d3585b79eaef2cd059150e6606e68ba&chksm=f8874126cec935b5ba1309f65e7309c9214b49253e86e8ae6eb85ff8a9f5b9cd2550c1cb57ee&scene=126&sessionid=1793283305#rd

## Summary

A research team from Harvard, Nvidia, Berkeley, MIT and Stanford proposed RAX (Robot Agent eXploration), which connects a general coding agent to robot perception and control interfaces, uses online exploration to write successful decisions into executable programs and accumulate them as skills, while keeping model parameters frozen.