Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
TL;DR
Evaluating two LRMs against controls lacking the proposed recurrence or curriculum, it is found these patterns also appear in the controls and do not consistently affect behavior, and latent thoughts should be treated as hidden computation, not hidden explanation.
Abstract
Latent reasoning models (LRMs) replace explicit chain-of-thought with continuous thoughts. Recent work treats observable latent-state patterns, such as BFS-like frontiers and decodable arithmetic computation, as evidence for internal reasoning mechanisms. Evaluating two LRMs (Coconut and CODI) against controls lacking the proposed recurrence or curriculum, we find these patterns also appear in the controls and do not consistently affect behavior. Causal interventions reveal that latent-thought utilization is not binary but graded, scaling with a thought's causal effect on model behavior. Geometric analyses reveal this effect concentrates in low-dimensional subspaces whose step-wise geometry grows more structured as their behavioral influence increases. Latent thoughts should therefore be treated as hidden computation, not hidden explanation: decodability, attention, or static structure alone cannot establish LRM reasoning mechanisms; that requires matched controls and causal tests.
