Search papers, labs, and topics across Lattice.
This paper introduces G-RRM, a neuro-symbolic framework that combines symbol-equivariant recurrent reasoning models (SE-RRMs) with classical symbolic solvers to enhance the efficiency of solving constraint satisfaction problems. The authors demonstrate that the effectiveness of this guidance hinges on the problem's combinatorial complexity and the solver's ability to adaptively overwrite branching decisions. Experimental results reveal that G-RRM significantly accelerates backtracking and SAT-based solvers like Glucose 4.1, achieving speedups of up to 33.3 times on 9x9 Sudoku puzzles, while highlighting the limitations of solvers like CaDiCaL 3.0.0 that do not adaptively incorporate neural hints.
Neural guidance can reduce median conflict counts to zero and dramatically speed up symbolic solvers, but only under specific conditions.
In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a neuro-symbolic approach, ``Guiding with Recurrent Reasoning Models''(G-RRM), which integrates SE-RRMs with symbolic solvers for constraint satisfaction problems. SE-RRMs act as neural solvers that generate full solution proposals and guide classical symbolic solvers, such as backtracking or SAT-based methods like Glucose 4.1 and CaDiCaL 3.0.0, that produce globally correct solutions. Centrally, we investigate when neural guidance with G-RRM improves the search efficiency of symbolic solvers. % Our experiments show that the efficacy of G-RRM depends on two conditions: first, the problem instances must have an expansive combinatorial search space to expose potential gains, and second, the solver architecture must be capable of dynamically overwriting its branching choices to recover when neural hints are imperfect. When these conditions hold, guidance drives median conflict counts to zero and yields significant wall-clock speedups: on $9\times9$ Sudoku, where the SE-RRM correctly solves $91.1\%$ of instances, backtracking accelerates by $33.3\times$ and Glucose 4.1 by $1.70\times$ (median, $p<0.001$), with Glucose 4.1 retaining a $1.17\times$ speedup on perfect-hint $25\times25$ grids. In contrast, CaDiCaL 3.0.0, whose runtime is overhead-dominated and which always respects the injected branching hints rather than overwriting them, shows no significant speedup (median $1.02\times$, n.s.) and even a small significant mean slowdown ($0.90\times$) on $9\times9$. These results delineate the regimes in which neural guidance translates into practical speedups.
