Exploiting Configurations of MaxSAT Solvers
Alòs, Josep, Ansótegui, Carlos, Salvia, Josep M., Torres, Eduard
–arXiv.org Artificial Intelligence
Since 2006, the MaxSAT Evaluation (MSE) Bacchus et al. [2022] has been held annually with the primary objective of advancing MaxSAT technology and assessing its current state-of-the-art. The evaluation consists of multiple solvers being tested on various benchmarks across different evaluation tracks. This event has undeniably spurred the MaxSAT community to create more cutting-edge solvers and enhance their competitiveness. It is not surprising that solver performance depends on several factors, including the power of the algorithm implemented by the solver, proper configuration of solver parameters to unleash its full potential, and implementation issues. Therefore, we must interpret the MaxSAT Evaluation ranking results carefully and derive conclusions according to the goal of our analysis.
arXiv.org Artificial Intelligence
Jun-13-2023