跳到正文
The Decoder· Jonathan Kemper·· 2 天前AI 评分62

Google 研究提出 RRSI,防止自我改进智能体记忆测试任务

Google researchers find a way to keep self-improving AI agents from memorizing their tests

AI 导读

Google 研究人员在论文中提出 RRSI(Regularized Recursive Self-Improvement of Agent Harnesses),用于约束智能体对自身 harness 的递归自我优化,避免其记忆测试任务。

来源:The Decoder · the-decoder.com