Research2026-05-12
MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
Source: Arxiv CS.AI
arXiv:2605.08498v1 Announce Type: cross Abstract: We introduce MathConstraint, a hard, adaptive benchmark for evaluating the combinatorial reasoning capabilities of LLMs. We combine constraint satisfaction problems with rigorous solver-based verification and design an adaptive generator to create...
arxivpapersreasoning