[Submitted on 10 Jun 2026 (v1), last revised 24 Oct 2026 (this version, v2)]
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.
Submission history
From: Darpan Aswal [view email]
[v1] Wed, 10 Jun 2026 21:23:22 UTC (318 KB)
[v2] Sat, 24 Oct 2026 15:35:35 UTC (2,735 KB)
