# Tsinghua, AgiBot and Infinigence AI propose Collective Experience Learning (CEL), validated on 96 real robots for scalable gains

- Source: 机器之心 · 微信公众号
- Published: 2026-10-30T04:22:49.000Z
- RoboHot: https://robohot.news/en/items/g6szn1mt81rb4c6zpkpgivo7f
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651071094&idx=1&sn=ffb10bdd4e9e7a7c0f3d65a0aff29758&chksm=85371a395b028e8cbe5a98469d5a9dcb301141859954147bcf99f25d86adea3647e637572a3d&scene=126&sessionid=1793371799#rd

## Summary

Tsinghua University, AgiBot and Infinigence AI jointly proposed the Collective Experience Learning (CEL) paradigm and completed prototype validation on 96 robots. In a phone-packaging task, the trained policy completed 120 tests on two robots of the same model that did not participate in training, raising the success rate from 79.2% to 98.3% and reducing failures from 25 to 2.