CoRD：耦合式 rollout 填补 on-policy 蒸馏的盲区

Authors:Guhan Chen, Bohan Li, Jun Rao, Hejin Wang, Songtao Tian, Yexin Xie, Xiaojun Meng, Peng Yuan, Jiansheng Wei, Xuebo Liu, Zixiong Yu

View PDF HTML (experimental)

Abstract:On-policy distillation trains a student on its own rollouts, so states the teacher would reach but the student does not are seldom supervised. We introduce CoRD (coupled-rollout distillation), which keeps the on-policy loss and moves only the distribution of training states toward the teacher, drawing rollouts from a geometric interpolation of student and teacher through the maximal coupling of speculative decoding. The coupling keeps the student's token wherever the two distributions agree and otherwise substitutes a token from the part of the target the student underweights, so interventions are as rare as any exact sampler allows and recede as the student learns. Across six base students from two model families (Qwen3 and Qwen3.5, 0.6B to 4B), CoRD raises average pass@1 over on-policy distillation by 0.9 to 2.0 points and pass@8 by 1.2 to 3.4 points on five public math benchmarks at equal steps and data. On frozen teacher-reached states, a 4B student trained with CoRD reaches in 16 steps a gap closure that on-policy distillation does not reach in 80, and substitution rules intervening at least as often in other directions fall short of CoRD.

Subjects:	Machine Learning (cs.LG); Computation and Language (cs.CL)
Cite as:	arXiv:2611.07959 [cs.LG]
	(or arXiv:2611.07959v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2611.07959 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zixiong Yu [view email]
[v1] Thu, 5 Nov 2026 12:55:51 UTC (1,781 KB)