1
Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?
新研究揭示LLM裁判在代理任务中打分不可靠，瓶颈与改进思路值得关注
arXiv:2606.29920v1 Announce Type: new Abstract: Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Ju…