1
Enhancing LLM Metacognition via Cognitive Pairwise Training
认知配对训练让LLM学会反思自身知识边界，元认知能力显著提升。
arXiv:2606.00869v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its out…