Michal Pluhacek

This paper presents EASE (Effortless Algorithmic Solution Evolution), an open-source and fully modular framework for iterative algorithmic solution generation leveraging large language models (LLMs). EASE integrates generation, testing, analysis, and evaluation into a reproducible feedback loop, giving users full control over error handling, analysis, and quality assessment. Its architecture supports the orchestration of multiple LLMs in complementary roles - such as generator, analyst, and evaluator. By abstracting the complexity of prompt design and model management, EASE provides a transparent and extensible platform for researchers and practitioners to co-design algorithms and other generative solutions across diverse domains.

We propose a framework for automated discovery and composition of metaheuristic operators using large language models (LLMs). The method begins with generation of candidate algorithms, followed by LLM-guided selection of impactful operators, iterative construction of specialized operator variants, and final synthesis of an adaptive optimizer. The approach emphasizes task coverage rather than single-metric optimization, producing complementary operators specialized for different problem characteristics. These operators are subsequently integrated into an adaptive algorithm via LLM-driven parameter control and selection mechanisms. This work is submitted as a competition entry for LLM-generated metaheuristics evaluated on the GNBG benchmark.

Numerous studies have proposed a wide range of features for Boolean SAT (satisfiability) problems, primarily aimed at predicting solver runtime or guiding algorithm selection. In this study, we investigate whether SAT instance features can be leveraged to predict suitable Island Genetic Algorithm (IGA) parameter settings for a given SAT instance. Our results indicate that even a single SAT feature is sufficient to guide the selection of IGA parameter settings with reasonable performance. We analyze this phenomenon by training an ensemble of machine learning models on progressively smaller subsets of features and evaluating how performance degrades as features are removed. In particular, models trained on a single feature typically retain at least 90% of the performance achieved by models trained on the full feature set. Moreover, several parameters can be accurately predicted using only basic SAT statistics, such as the number of clauses and variables. Additionally, it can be observed from the results that certain features have strong generalization ability and can serve as proxies for a set of other features when predicting IGA parameter settings. Overall, our findings demonstrate that a small set of simple SAT features yields a practical and transferable signal for instance-specific IGA parameter selection.

Steam-filled chambers are an important part of many technological processes, among others, in tire manufacturing and electricity production from thermal power plants. This work proposes a chamber model as a strongly nonlinear process with time-delays, where parameters depend on operating conditions and may vary in time. To identify system parameters, a parametric optimization task is formulated that minimizes the fit of the model to factory-measured data under varying valve opening conditions. Two significantly different approaches were used to solve this nonlinear optimization task. The first utilized local and semi-local optimization with prior knowledge derived from solving a simplified variant of the task. The second used global optimization methods without any prior knowledge. The obtained parametric models were compared based on the quality of fit and the sensitivity and stability analysis of the obtained solutions. The achieved models reflect real data with high accuracy, with mean squared errors as low as 0.0138 on output values ranging from 0.0 to 20.0, representing less than 0.1% of the output range. The solutions differ significantly in the values of the obtained parameters. The use of multiple methods has thus made it possible to obtain a diverse set of solutions, which is particularly valuable in applications for difficult engineering problems. Results of this work can be further used e.g. for subsequent step - optimal control system design for the given process and operating conditions.