技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
surgical-post-training-error-correction【数据与研究】Correct reasoning errors with minimal data collection by using an oracle to surgically fix only erroneous steps in existing trajectories. Use binary classification loss on rectified pairs with implicit KL regularization to prevent knowledge forgetting.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准