Neural Reasoners in Sudoku Act as One-Shot Predictors, Not Iterative Searchers
A new arXiv preprint finds that the Lattice Deduction Transformer (LDT), a neural solver for Sudoku, commits to nearly all answers in a single forward pass, rather than performing iterative search as commonly assumed. The study shows that adding search mechanisms like backtracking does not improve which puzzles are solved, but only reduces redundant computation. The authors introduce symmetry-based interventions that dramatically boost accuracy on 9x9 Sudoku from below 1% to over 96%.
Why it matters: This work challenges the prevailing view that neural solvers perform iterative reasoning, suggesting that their effectiveness in clue-rich tasks depends more on calibration and symmetry than on search.
Full story at: arXiv Machine Learning ↗