The Decoder· Jonathan Kemper·· 5 小时前AI 评分74
Sakana AI 与 UC Berkeley 提出 MASS 递归自我改进方法
Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots
AI 导读
Sakana AI 与 UC Berkeley 提出 Multi-Agent Self-Supervision(MASS),让同一语言模型分别承担任务执行、结果评估和工作流优化,并通过 LoRA 微调进行递归改进。
来源:The Decoder · the-decoder.com