On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own reasoning, weakening its feedback on later tokens. Updates based on this feedback can reinforce the same deviations in later resp...
Jian-Nan Guan, You-Xin Jiang, Yu-Tai Hou et al.· 0 citations
Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing settings often leave agents to rebuild routine infrastructure or restrict exploration to individual components. We introduce RSIG...
Fan-Qing Meng, Ling-Xiao Du, Hao-Cheng Lu et al.· 3 citations
This work presents a pipeline that unfolds each paper into a multi-turn generation trajectory in which a teacher model reconstructs the writing process of the whole paper: a writing request, a global plan, and pre-writing deliberation for each section.
Qianchuan Xu, Qiguang Chen, Zi-Jian Su et al.· 0 citations
The Causal-Generative Dual-Judge (CGDJ) is introduced, auditing World Model Consistency from two perspectives, and analysis exposes audio-visual misalignment, where models verbalize correct causal logic more reliably than they render it, challenging the"world simulator"narrative.
