👋 At 10:15 PST this morning we’ll be covering this Agent-as-a-Judge paper. This is brand new research from Meta that introduces the Agent-as-a-Judge framework, wherein agent systems are used to evaluate (you guessed it) agent systems.
According to the paper authors: “This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process.”
Join us here: https://arize.com/resource/community-papers-reading/