GPD (Geometry-Privileged Distillation) is proposed, which makes geometric evidence the privilege in on-policy self-distillation (OPSD), outperforming both GRPO and answer-privileged OPSD across spatial reasoning benchmarks.
Hong-Xing Li, Yi-Xin Li, Ding-Ming Li 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
MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.
En-Ze Ma, Yufan Zhou, Wei-Chieh Huang et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.