AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Prediction Dynamics in Depth-Recurrent Language Models

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Depth-recurrent language models refine predictions through repeated latent updates. Why can intermediate answers agree with the endpoint while their scores continue to change? We derive a sharp margin characterization that decomposes the conservatism of a magnitude bound into common translation, direction relative to the winner, and the pairing of each competitor's update with its score gap. Across Huginn-3.5B and Ouro-1.4B, accounting for update direction and competitor pairing reduces the mean earliest qualifying depth by a further 22.5-34.4% of the total depth beyond translation removal und

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T14:01:59.594Z. This is not the publication date.