1
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
揭秘推理模型“表演性思维链”：模型已确信答案却不暴露内部信念，引发对AI推理真实性的深层思考。
arXiv:2603.05488v4 Announce Type: replace-cross Abstract: We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a mode…