A. Malakhov

ESSA: Evolutionary Strategies for Scalable Alignment

ESSA (Evolutionary Strategies for Scalable Alignment), a gradient-free online alignment stage that follows supervised fine-tuning (SFT) and replaces the gradient loop with inference-only black-box search, is presented.

: The University of Arkansas Undergraduate Research

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

A difficulty-aware scaling coefficient is proposed, inspired by Focal loss, that down-weights updates on high-success sampled groups and improves average math pass@256 in all three cases, without increasing group size or computational cost.