Teach to Learn: Hint Annealing for Self-improving LLM Reasoning
Group Relative Policy Optimization (GRPO) improves language-model reasoning by comparing verified rewards among multiple solution rollouts for each query. However, difficult training queries can yield only incorrect rollouts, leaving GRPO with no reward contrast or learning signal. Prior hint-based methods construct au...
Zi-Le Wang, Zi-Jian Li, Hao-Dong Wang et al.
· 0 citations