On-policy distillation (OPD) trains a student on its own reasoning trajectories using feedback from a stronger teacher. Teacher interventions can improve these trajectories, but also change the distribution on which the student learns. Our controlled studies show that rollout quality alone is an incomplete criterion fo...
Yu-Hao Wang, Ruiyang Ren, Yi-Nan Zhang et al.· 0 citations
A Gaussian guidance framework that draws the depth per task from a Gaussian whose center and spread are estimated online from rollouts already collected for policy optimization, requiring no probe rollouts or learned depth predictor is proposed.
Zi-Xuan Wang, Yan-Rui Miao, Zhengxi Lu et al.· 2 citations
This paper proposes CRISP, a framework for training efficient deep search agents through critical step perception that distinguishes interactions that gather necessary evidence from redundant ones and shapes the training reward to preserve the former while pruning the latter, improving efficiency without sacrificing th...
Haosi Mo, Zihao Yan, Ruiqing Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.