Hint Tuning: Less Data Makes Better Reasoners 事件

Hint Tuning: Less Data Makes Better Reasoners arXiv:2605.08665v2 Announce Type: replace Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We propose Hint Tuning, a data-efficient approach that teaches models to calibrate reasoning depth. Our key insight: the corresponding instruct model serves as an ideal difficulty probe. By testing what th