arXiv:2608. 15958v1 Announce Type: new Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificate to check.
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.
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. 19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states.
arXiv:2609.38806v1 Announce Type: cross Abstract: Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on prob...
Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that.
arXiv:2606. 15686v1 Announce Type: new Abstract: Large language models often appear strong on symbolic and algorithmic tasks, yet this apparent strength can hide brittle behaviour when problems become longer, harder, or slightly out of distribution.
arXiv:2608.27757v1 Announce Type: new Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc...
arXiv:2608. 07077v1 Announce Type: new Abstract: The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large reasoning models (LRMs).
arXiv:2607. 20171v1 Announce Type: cross Abstract: Learned solvers for compressible flow are usually compared to classical methods at equal mesh resolution rather than at equal computational cost, and they typically offer no guarantee that their solutions remain physically admissible.
LLM‑BabyBench transforms the BabyAI gridworld into a fully observable, purely textual setting that isolates planning as the sole source of failure. By serialising the entire grid, providing formal instructions, and validating actions deterministically, the benchmark introduces the PPD suite—Predict, Plan, and Decompose tasks—each scored with metrics that separate mission understanding from sequencing. Across a range of large language models, simulation accuracy is high while planning success drops sharply beyond a model‑specific horizon, revealing that plan length—not grid size—drives failure and that models often commit to a single corridor‑shaped route without backtracking.
arXiv:2608. 00301v1 Announce Type: new Abstract: Error-penalized scoring rules ($+1$ for a correct answer, $-\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\ast=\lambda/(1+\lambda)$.
arXiv:2609. 18966v1 Announce Type: new Abstract: Linear RNNs with input-dependent Householder-product transitions (DeltaNet/DeltaProduct-class) can provably represent hard state-tracking automata, yet trained models fail to length-generalize -- a gap recent work attributes to optimization, without a causal account.