Rubrics Survey: How to Define a Good Answer in the Agent Era

Rubrics综述：Agent时代，如何定义一个「好答案」？

Renmin University Gaoling School of Artificial Intelligence released a 40-page survey on rubrics for LLMs, organizing the topic into five parts: definitions, construction methods, training uses, evaluation scenarios, and open challenges.

Why it matters: HKR-H/K/R all pass, but this is a survey rather than a model or product launch. The 40-page rubric framework is useful for agent evaluation, placing it at the featured threshold.