arXiv cs.AI
Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
멈추는 법을 배우기 전에 멈추는 법을 배우기: 자기지도 신뢰 훈련이 추론 효율성을 향상시킨다
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.