# AgiBot releases embodied model GO-3 Preview, enabling full-pipeline scaled learning from pretraining to post-deployment

- Source: 机器之心 · 微信公众号
- Published: 2026-10-29T10:03:24.000Z
- RoboHot: https://robohot.news/en/items/wfe2h2ddz3oiiyv2cy0fh6h5j
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651070983&idx=1&sn=d47470e0625fe320c1c43284d25520bc&chksm=85dd2ecc87d372a1f86a5d59925a135906cd11b0b69faedcf6b3b365bdcff234fb39627aa6f1&scene=126&sessionid=1793284300#rd

## Summary

AgiBot has released the embodied model GO-3 Preview, focused on full-pipeline scaled learning across pretraining, post-training, and post-deployment, and it ranked first in three evaluations: RoboDojo, RoboTwin, and RoboColiseum.

## Why it matters

AgiBot disclosed GO-3 Preview's three-stage learning pipeline of pretraining, post-training, and post-deployment, along with specific benefit data from mixed training using real-machine clusters and world models.