Teach to Learn: Hint Annealing for Self-improving LLM Reasoning
HATCH (Hint-Annealed Self-Teaching), an online single-policy framework that learns from both generating and using its own hints to improve reasoning without assistance, is proposed and gradient projection is used to remove the opposing component of hint-generation updates.
Zi-Le Wang, Zi-Jian Li, Hao-Dong Wang et al.
· 0 citations