1
From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
大模型推理新突破：通过认知对齐后训练，从元思维到执行提升泛化性与可靠性
arXiv:2601.21909v2 Announce Type: replace Abstract: Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine…