The Decoder· Jonathan Kemper·· 5 小时前AI 评分57
Google 研究者提出 RRSI,减少自我改进智能体对测试任务的记忆
Google researchers find a way to keep self-improving AI agents from memorizing their tests
AI 导读
Google 研究者提出 RRSI(Regularized Recursive Self-Improvement of Agent Harnesses),通过约束 harness 的自我优化,减少智能体记忆测试任务并改善未见任务表现。
来源:The Decoder · the-decoder.com