Preprint
Jul 2026
LeAct: Learning to Reason from Expert Actions
The approach, LeAct (Learning to reason from Actions), optimizes this latent variable: the student samples candidate CoTs for each expert action, and the student retains those that measurably improve its own probability of recovering the action.
Ziran Yang, Chengshuai Shi, Raj Ghugare et al.
· 0 citations