Learning can run backward： begin with an expert action， discover the reasoning behind it， then teach the model to reason forward.
Paper：
LeAct： Learning to Reason from Expert Actions
AI 摘要
学习可以反向进行：从专家行为出发，发现其背后的推理过程，然后教会模型正向推理。 论文： LeAct：从专家行为中学习推理
Learning can run backward： begin with an expert action， discover the reasoning behind it， then teach the model to reason forward.
Paper：
LeAct： Learning to Reason from Expert Actions