#sat-solvers News & Analysis

4 articles tagged with #sat-solvers. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · May 127/10

🧠

MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs

Researchers introduced MathConstraint, an adaptive benchmark for testing large language models' combinatorial reasoning abilities using constraint satisfaction problems with automated verification. The benchmark reveals significant performance gaps between frontier models, with accuracy dropping from 72-87% on easier instances to 18-66% on harder ones, while tool access via Python solvers roughly doubles performance.

🧠 GPT-5

AINeutralarXiv – CS AI · Mar 57/10

🧠

A Geometric Perspective on the Difficulties of Learning GNN-based SAT Solvers

Researchers explain why Graph Neural Networks (GNNs) struggle with complex Boolean Satisfiability Problems (SATs) through geometric analysis using graph Ricci Curvature. They prove that harder SAT instances have more negative curvature, creating connectivity bottlenecks that prevent GNNs from effectively processing long-range dependencies.

AIBullisharXiv – CS AI · 5d ago6/10

🧠

Discovering heuristics in a complex SAT solver with large language models

Researchers have developed AutoModSAT, a framework that leverages large language models to automatically discover and optimize heuristics in SAT solvers, achieving 40% performance improvements over baseline solvers. The approach combines modular solver design with LLM-guided function generation and evolutionary algorithms, demonstrating significant practical gains across diverse datasets.

AINeutralarXiv – CS AI · May 116/10

🧠

Bounded Fitting for Expressive Description Logics

Researchers extend bounded fitting—a machine learning paradigm for logical formula discovery—to more expressive description logics beyond ALC, maintaining PAC-style guarantees while implementing practical solutions via SAT solvers. The work demonstrates that this approach scales to complex logical systems with inverse roles and qualified restrictions, achieving competitive results against existing concept learners.