SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning
This work introduces SPEAR (Symbolic Process Evaluation and Alignment Reward), a training-free and plug-and-play process reward method for sequence-level on-policy distillation that effectively bridges the reasoning gap between student and teacher models via sequence-level distillation with efficient dense process rewards.
Zhuochun Li, Yuelyu Ji, Yiming Zeng et al.
· 0 citations