Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-time early-stopping mechanisms or by explicitly encouraging shorter reasoning during training, for example through reinforcement learning with length penalties. We show that substantial efficiency gains can instead emerge…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
