The field of optimization and process mining is witnessing significant advancements, driven by the integration of machine learning, evolutionary algorithms, and novel modeling approaches. Researchers are exploring new initialization strategies, hybrid methods, and neuro-symbolic approaches to improve the performance and efficiency of optimization algorithms. Additionally, there is a growing focus on process discovery, with a emphasis on capturing complex decision-making behavior and non-block-structured decisions. The development of more effective evaluation methodologies is also crucial, as highlighted by the pitfalls of benchmarking in algorithm selection. Noteworthy papers in this area include:

• the introduction of a hybrid initialization strategy that combines empty-space search algorithm and opposition-based learning to enhance population diversity and accelerate convergence.
• a neuro-symbolic approach that refines candidate interpretations returned by a sequence tagger using an Abstract Argumentation Framework-based reasoner, allowing for more efficient and accurate analysis of event sequences.
• the proposal of an extension to the Partially Ordered Workflow Language to handle non-block-structured decisions through the introduction of choice graphs, enabling more precise representation of complex decision-making behavior in real-world processes.