Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning

ArXi:2605.16824v1 Announce Type: new Large language models (LLMs) generate not only reasoning text, but also token-level confidence trajectories that record how uncertainty evolves during inference. Whether these trajectories are relevant to reasoning correctness remains unclear. Here we show that confidence trajectories encode a content-agnostic confidence geometry associated with trace-level final-answer correctness.