Skip to content
Hot eventLive

ReTeach:反思式自蒸馏框架构建自教师

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv(Artificial Intelligence,一手来源)发布关于ReTeach的报道。ReTeach提出一种反思式自蒸馏框架,仅使用自生成尝试与结果级验证,通过多轮反思与重试构建自教师,无需参考答案、外部诊断反馈或跨样本记忆。该框架采用结果感知的选择与加权策略,对初始正确、反思纠正和未解决样本分别赋权,并通过on-policy蒸馏在学生自身rollout前缀上对齐教师的token级预测分布。目前公开信息仅涉及该框架的方法设计,未见实验结果或后续进展报道。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Artificial Intelligence
    ReTeach:通过多轮反思与重试构建自教师

    ReTeach 提出一种反思式自蒸馏框架,仅用自生成尝试与结果级验证,通过多轮反思与重试构建自教师,无需参考答案、外部诊断反馈或跨样本记忆。该框架采用结果感知的选择与加权策略,对初始正确、反思纠正和未解决样本分别赋权,并通过 on-policy 蒸馏在学生自身 rollout 前缀上对齐教师的 token 级预测分布。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.