arXiv:2606. 06518v1 Announce Type: new Abstract: Sudoku is a representative constraint satisfaction problem that requires global structural reasoning under strict discrete constraints.
arXiv:2606. 29150v1 Announce Type: new Abstract: Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puzzles, they converge confidently to incorrect answers (solving only $\sim$36% of Sudoku puzzles).
arXiv:2607. 27169v1 Announce Type: new Abstract: Solving a continuous algebraic constraint system requires two decisions: which values satisfy the constraints, and which structural augmentation renders an unsolvable system solvable.
Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting which tokens become confident, which remain unstable, and when commitments form.
arXiv:2607. 02491v1 Announce Type: new Abstract: In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes.
arXiv:2608. 14569v1 Announce Type: new Abstract: Neural solvers for constraint satisfaction problems have achieved remarkable in-distribution accuracy, yet they suffer from a fundamental limitation persistent constraint violations occur under distribution shifts even when the model reports high confidence.
arXiv:2607. 19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states.
Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that.
arXiv:2607. 28954v1 Announce Type: new Abstract: Branch and Bound (BaB) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems.
arXiv:2607. 01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces.
arXiv:2608. 08677v1 Announce Type: new Abstract: Skill evolution improves agent skills through feedback over time, with failed trajectories often providing informative signals by revealing incomplete or misleading behaviors.
arXiv:2606. 23880v1 Announce Type: new Abstract: From climate teleconnections to gene regulation, modern time-series datasets encompass tens or hundreds of interacting variables, making causal discovery increasingly challenging.
arXiv:2604. 24357v2 Announce Type: replace-cross Abstract: Diffusion language models generate without a fixed left-to-right order, leaving token ordering as a central algorithmic choice.