听说挺猛的可以把LLM Agent的skill文档当神经网络的权重来训练
但是也不知道具体效果咋样 反正token有点起飞了
GitHub - microsoft/SkillOpt: SkillOpt is a text-space optimizer that trains...
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
1 个帖子 - 1 位参与者
来源: LinuxDo 最新话题查看原文