2 papers
cs.AI2026
Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation
Jiaxuan Wang, Jiafei Lyu, Yuchen Cai +8
On-policy distillation (OPD) trains students using teacher feedback on their own sampled responses, yet how prompt choice shapes transfer across teacher-student pairs remains poorl…
cs.LG2026
Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
Yuchen Cai, Ding Cao, Qixiang Yin +10
Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the high dimensionality of parameter updates makes its training dyna…