On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models. Without external rewards nor a separate stronger teacher, the self-teacher with privileged information could provide dense signals on student's trajectories. However, its behavi...
Yang Li, Gong-Le Xue, Yu-Heng Yuan et al.· arXiv.org· 0 citations
It is argued that OPSD is a sensitive algorithm rather than a generally reliable reasoning-improvement post-training method because it produces ineffective length growth, stable degradation, or behavioral collapse.
Yang Li, Gong-Le Xue, Yu-Heng Yuan et al.· 0 citations
RoboFoundry is proposed, the first embodied agentic framework that formulates this process of system-as-policy evolution across foundation models as Self-Evolving System-as-Policy, highlighting its potential for fully autonomous embodied agents.