LLM Reasoning Is Latent, Not the Chain of Thought

ArXi:2604.15726v1 Announce Type: new This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surface chain-of-thought (CoT). This matters because claims about faithfulness, interpretability, reasoning benchmarks, and inference-time intervention all depend on what the field takes the primary object of reasoning to be.