test-time-scaling-reflective

【开发与工程】Scale model performance at test time by generating multiple reasoning trajectories and selecting the best using a self-supervised process reward model. MetaStone-S1 achieves 32B-equivalent performance using only 32B parameters and 53M for trajectory scoring, learning process rewards from outcome labels alone without process annotations.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准