# Harvard, Berkeley, NVIDIA and others propose RAX, using online exploration scaling to let robots learn skills with zero demonstrations

- Source: 机器之心 · 微信公众号
- Published: 2026-10-25T09:00:35.000Z
- RoboHot: https://robohot.news/en/items/twjr7975rxqrq5gqd8ycovbbs
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651069945&idx=2&sn=dc9829c3d689d8f2438948978e7607ac&chksm=85cca94af2ca98ee89f8a04c1c5fb583d12c75446c699a502d824edf71991bc651484e00bd6d&scene=126&sessionid=1792927934#rd

## Summary

A research team from Harvard, NVIDIA, Berkeley, MIT and Stanford proposes 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 reusable skills, while keeping model parameters frozen.

## Why it matters

RAX uses a frozen model plus online exploration to generate reusable programs, leading by an average of 37.4 percentage points on five simulation benchmarks with zero action demonstrations, offering a path for robot learning different from scaling data and models.