WHAT NEW IN X11.02 MON

X 上的 AI 合集档案 · 22 个合集 · 65,263 条

agentVIDEO

Reppo Eval API 上线多代理评估工作流

Eval API 新增多代理评估,让协作代理获得互不污染的独立反馈,面向安全与医疗等场景。

Reppo
@reppo2026.10.03收录原推发布于 2026.10.03
Reppo @reppo原推发布于 2026.10.03
在 X 上打开原推

We have shipped multi agent eval workflows to the Eval API. This enables agents working together to access independent feedback + judgment without the eval being polluted by other agents which remains a pressing painpoint in multi agent systems, especially in high stakes workflows like cybersecurity, defense, and healthcare. ⛽️⛽️⛽️

x.com/reppo/status/2106125721076924887采集于 2026.10.03 10:31