Sudoku Solving

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

When Recursive Models Finish Computing
Sep 22, 2026Hare Krishna, Shubham Singh, Stephen Ebert +1Sudoku Solving Recurrent Neural Networks
Weinberg Institute, Department of Physics, University of Texas at Austin · Department of Urban and Environmental Policy Planning, Tufts University · Zyphra Technologies, San Francisco, CA, USA +2
Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion
Jul 22, 2026Aleksey KomissarovSudoku Solving Inference-Time Search
Neapolis University, Pafos, Cyprus
Graph Coloring Approach to Solving Sudoku with Oscillatory Neural Networks
Jul 17, 2026Filip Sabo, Aida Todri-SanialSudoku Solving Oscillatory Neural Networks
NanoComputing Research Lab, Electrical Engineering Department Eindhoven University of Technology Eindhoven, the Netherlands
MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku
Jul 14, 2026Pedro Orvalho, Guillem Alenyà, Felip ManyàVision-Language Models Sudoku Solving
Artificial Intelligence Research Institute (IIIA), Consejo Superior de Investigaciones Científicas (CSIC), Barcelona, Catalonia, Spain · Institut de Robòtica i Informàtica Industrial (IRI-CSIC-UPC), Barcelona, Spain
DiBS: Diffusion-Informed Branch Selection
Jun 2, 2026Bo Liu, Yuan Xie, Yuan Gao +4Sudoku Solving Diffusion Guidance
1Jilin University · 2The Chinese University of Hong Kong, Shenzhen · 3Southwest University +3
Lattice Deduction Transformers
May 9, 2026Liam Davis, Leopold Haller, Alberto Alfarano +1Sudoku Solving Abstract Interpretation
Amherst College · Axiom · Barnard College, Columbia University
Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
Apr 23, 2026Grigory SapunovMemory-Augmented Neural Networks Sudoku Solving
Intento
Dynamical Systems Theory Behind a Hierarchical Reasoning Model
Mar 24, 2026Vasiliy A. Es'kin, Mikhail E. SmorkalovSudoku Solving Neural Algorithmic Reasoning
Department of Radiophysics, University of Nizhny Novgorod, Nizhny Novgorod 603950, Russia · Huawei Nizhny Novgorod Research Center, Nizhny Novgorod 603006, Russia · Skolkovo Institute of Science and Technology, Moscow 121205, Russia
Symbol-Equivariant Recurrent Reasoning Models
Mar 2, 2026Richard Freinschlag, Timo Bertram, Erich Kobler +2Permutation-Equivariant Neural Networks Sudoku Solving
ELLIS Unit Linz, LIT AI Lab & Institute for Machine Learning, Johannes Kepler University Linz, Austria · Clinical Research Institute for Medical AI, Johannes Kepler University Linz, Austria
Toward a Universal Characterization of Sudoku Puzzle Difficulty
Jul 22, 2025Arman Eisenkolb-VaithyanathanSudoku Solving Boolean Satisfiability
Lynbrook High School, San Jose

Sep 22, 2026J/K move · Enter open · S save

When Recursive Models Finish Computing

Hare Krishna, Shubham Singh, Stephen Ebert, Hao-Yu Sun

Weinberg Institute, Department of Physics, University of Texas at Austin · Department of Urban and Environmental Policy Planning, Tufts University · Zyphra Technologies, San Francisco, CA, USA+2

Sudoku Solving Recurrent Neural Networks Algorithmic Reasoning

Open paper AskPDF arXiv

Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the dynamics of completion in attention- and MLP-based Tiny Recursive Models (TRMs) on 1,000 hard Sudoku puzzles. Extending recurrence from the nominal 16 steps to 512 steps increases cumulative exact-solve accuracy from 59.2% to 87.5% for the attention model and from 74.4% to 91.9% for the MLP model, solving more than two-thirds of the puzzles unsolved in the nominal budget. Across both architectures, latent-state motion drops sharply after the first exact solution. Completed states are typically locally contractive along the trajectory direction, even though the same local Jacobian retains strongly expanding directions. We characterize this phenomenon as trajectory-conditioned anisotropic stability. Perturbation experiments confirm this directional stability across both models. The multi-step fate of the maximally expanding direction differs: it is absorbed within 16 steps in the attention model but persists longer in the MLP model. The anisotropic-stability pattern also holds for a second attention checkpoint. Together, these results distinguish nominal-budget failure from completed computation and identify a common dynamical signature of completion across two recurrent architectures.