aiqbench analysis
AutoModSAT demonstrates that LLM-guided heuristic discovery can significantly outperform traditional parameter-tuning methods, achieving up to 40% performance gains and notable speedups on complex SAT solvers. By combining modular solver design with unsupervised prompt optimization, this approach effectively bypasses the limitations of manually constrained search spaces in automatic configuration. The results suggest a promising new direction for optimizing intricate computational architectures without relying on human-defined constraints.
Discovering heuristics in a complex SAT solver with large language models
arXiv:2507.22876v2 Announce Type: replace Abstract: The Satisfiability problem (SAT) is fundamental in computational complexity theory and has a wide range of industrial applications. Optimizing modern SAT solvers in real-world settings is quite challenging due to their intricate architectures. While automatic configuration frameworks have been developed, they rely on manually constrained search spaces. Here we develop AutoModSAT, a framework that uses large language models (LLMs) to automatically optimize SAT solvers. AutoModSAT combines an LLM-compatible modular solver design, unsupervised prompt optimization to diversify generated functions, and an efficient search procedure based on presearch strategy and a $(1+\lambda)$ evolutionary algorithm. Extensive experiments across a wide range of datasets demonstrate that AutoModSAT achieves $40\%$ performance improvement over the baseline solver and $30\%$ improvement over the state-of-the-art solvers. Moreover, AutoModSAT also attains a notable speedup compared to the parameter-tuned alternatives of the state-of-the-art solvers over most of the test datasets. These results demonstrate the potential of LLM-guided heuristic discovery for optimizing complex SAT solvers.
Abstract:The Satisfiability problem (SAT) is fundamental in computational complexity theory and has a wide range of industrial applications. Optimizing modern SAT solvers in real-world settings is quite challenging due to their intricate architectures. While automatic configuration frameworks have been developed, they rely on manually constrained search spaces. Here we develop AutoModSAT, a framework that uses large language models (LLMs) to automatically optimize SAT solvers. AutoModSAT combines an LLM-compatible modular solver design, unsupervised prompt optimization to diversify generated functions, and an efficient search procedure based on presearch strategy and a $(1+\lambda)$ evolutionary algorithm. Extensive experiments across a wide range of datasets demonstrate that AutoModSAT achieves $40\%$ performance improvement over the baseline solver and $30\%$ improvement over the state-of-the-art solvers. Moreover, AutoModSAT also attains a notable speedup compared to the parameter-tuned alternatives of the state-of-the-art solvers over most of the test datasets. These results demonstrate the potential of LLM-guided heuristic discovery for optimizing complex SAT solvers.
Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
arXiv:2507.22876 [cs.AI]
(or arXiv:2507.22876v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2507.22876 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design
arXiv · Oct 15, 2026
Large language models discover complementary heuristics for combinatorial optimization
Nature · Oct 1, 2026
MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble
arXiv · Aug 5, 2026
TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models
arXiv · Sep 16, 2026