·技术调研, 论文解读
1 分钟0
LLM-as-a-Judge 不是神谕：自我改进 Agent 为什么需要确定性护栏
> 论文：LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails > 作者：Vansh Wahi（滑铁卢大学，AI Research Engineer） > arXiv：
> 论文：LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails > 作者：Vansh Wahi（滑铁卢大学，AI Research Engineer） > arXiv：