iterated-local-searchlisted

# Iterated Local Search You are an expert in iterated local search (ILS) and single-solution metaheuristics for combinatorial optimization. This skill covers the ILS loop — embedded local search, perturbation ("kick") design, and acceptance criteria — plus perturbation-strength tuning, adaptive variants, and the use of ILS as the strong simple baseline that any proposed metaheuristic must beat. Use the framework below to assemble an ILS from a problem-specific descent and a well-matched kick, to tune its three or four parameters, and to diagnose stagnation in an existing implementation. ## Initial Assessment Establish the following before writing any code or recommending parameters: - **Problem class and representation.** Permutation (tours, schedules), binary selection, assignment, or mixed? The representation fixes which local searches and kicks are available. - **Existing local search.** Is there already a descent procedure? How long does one full descent take on a realistic instance? ILS runs the local search hundreds to thousands of times; a descent that takes minutes makes plain ILS impractical without truncation. - **Evaluation cost.** Is the objective cheap to evaluate? Is delta (incremental) evaluation available for the neighborhood moves? Without delta evaluation, the embedded local search usually dominates runtime by 95%+. - **Time budget.** Wall-clock seconds per run, and number of runs (seeds × instances). ILS parameters that win at 10 seconds dif