Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces

ArXi:2605.14358v1 Announce Type: cross Language models often generate long chain-of-thought traces, but it remains unclear how much of this reasoning is necessary for preserving the final prediction. We study this through the lens of overcomplete reasoning traces: generated traces that contain intermediate steps than are needed to the model's answer. We define the minimal core as the smallest subset of steps that preserves either the final answer or predictive distribution, and