APPS

Researchers propose R²PO, a method that decouples rollout and inference policies for LLM reasoning, achieving accuracy gains of 3.4% on MATH-500 and 1.3% on APPS. The approach attaches a lightweight R…

Researchers found that using diverse ensemble monitoring—combining multiple small monitors built from a single base model—outperforms both repeated sampling of the same monitor and a single, more cost…