The Decoder· Jonathan Kemper·· 3 小时前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 研究人员提出 RRSI(Regularized Recursive Self-Improvement of Agent Harnesses),通过在提出改动和筛选改动两端加约束,避免自我改进的智能体记忆测试任务。
来源:The Decoder · the-decoder.com