jevPOST
Jev-as-a-Judge: scoring agent output without generating text
Someone proposes using Jev as a judge model that can score agent output without generating text, though the post only offers the concept and a link.
Vaishnavi
@_vmlopsArchived 2026.09.20Originally posted 2026.09.20
Vaishnavi @_vmlopsOriginally posted 2026.09.20
Jev-as-a-Judge is a pretty wild idea a judge that doesn’t need to generate text to evaluate an agent.... 👀 https://t.co/bLf9RmJotO
This post quotes another post: “LangChain tests Jev against LLM judges for agent evaluation”
x.com/_vmlops/status/2101493231993098338Archived 2026.09.20 11:14