One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models

ArXi:2604.18839v1 Announce Type: cross Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel. On difficult problems, such as those that require search-like computation, reaching a highly structured solution starting from noise can require long refinement trajectories. Learning such trajectories is challenging when.