# Obliczenia ewolucyjne i inteligencja roju

EN: **Evolutionary computation and swarm intelligence** · id `evolutionary` · aliases: evolutionary computation, evolutionary algorithms, nature-inspired optimization, metaheuristics, algorytmy ewolucyjne, obliczenia ewolucyjne, metaheurystyki

Path: [AI Atlas](https://aiatlasgraph.com/llms.txt) › Obliczenia ewolucyjne i inteligencja roju

## Description

- PL: Populacyjne metody optymalizacji i przeszukiwania inspirowane ewolucją i zachowaniami zbiorowymi, działające bez gradientu, tylko na ocenach kandydatów.
- EN: Population-based optimisation and search methods inspired by evolution and collective behaviour, working without gradients, only on candidate scores.

## In one sentence

- PL: Rodzina metod, które szukają dobrych rozwiązań jak natura: tworzą wiele wariantów, sprawdzają je i rozwijają najlepsze.
- EN: A family of methods that search for good solutions the way nature does: make many variants, test them, build on the best.

## Problem it solves

- PL: Wiele problemów nie ma wzoru na rozwiązanie, a sprawdzenie wszystkich możliwości zajęłoby wieki.
- EN: Many problems have no formula for the answer, and checking every possibility would take ages.

## What it does

- PL: Działa jak hodowca: z każdego pokolenia zostawia najlepsze osobniki, krzyżuje je i lekko zmienia, aż potomstwo jest coraz lepsze.
- EN: It works like a breeder: keep the best of each generation, cross them, change them slightly, and offspring keep improving.

## Everyday example

- PL: Firma kurierska co noc układa trasy setek aut; program próbuje tysięcy wariantów i zachowuje te, które skracają przejazdy.
- EN: A courier firm plans routes for hundreds of vans every night; software tries thousands of variants and keeps those that shorten trips.

## This concerns you if you…

- PL: umiesz ocenić rozwiązanie, ale nie wiesz, jak je wyprowadzić
- PL: szukasz kilku różnych dobrych wariantów, nie jednego
- PL: chcesz, by program sam wymyślał i ulepszał kod
- EN: can score a solution but cannot derive one
- EN: want several different good options, not just one
- EN: want software that invents and improves code by itself

## Keywords

genetic algorithms · CMA-ES · genetic programming · NSGA-II · particle swarm optimization · ant colony optimization · differential evolution · MAP-Elites · novelty search · NEAT · evolution strategies · AlphaEvolve · FunSearch · pymoo · DEAP

## How it works

- PL: Algorytm utrzymuje populację kandydatów, ocenia je funkcją przystosowania i tworzy następne pokolenie przez selekcję, krzyżowanie i mutację albo przez ruch w roju. Rodziny różnią się reprezentacją: ciągi bitów, wektory liczb, drzewa programów, sieci neuronowe, a ostatnio kod generowany przez modele językowe.
- EN: The algorithm keeps a population of candidates, scores them with a fitness function and builds the next generation through selection, recombination and mutation, or swarm movement. Families differ in representation: bit strings, real vectors, program trees, neural networks and, recently, code generated by language models.

## Limits

- PL: Potrzebuje wielu ocen kandydatów, więc kosztowna ewaluacja szybko dominuje. Brak gwarancji znalezienia optimum, wyniki zależą od reprezentacji, operatorów i parametrów; przy gładkich, różniczkowalnych problemach metody gradientowe są zwykle szybsze.
- EN: It needs many candidate evaluations, so expensive scoring quickly dominates. There is no guarantee of the optimum; results depend on representation, operators and parameters. On smooth differentiable problems gradient methods are usually faster.

## Key terms

- PL: **populacja**: Zbiór kandydatów rozwijanych równolegle w kolejnych pokoleniach.
- PL: **funkcja przystosowania (fitness)**: Ocena mówiąca, jak dobre jest dane rozwiązanie.
- PL: **optymalizacja czarnej skrzynki**: Szukanie najlepszych ustawień, gdy znamy tylko wynik, nie wzór.
- EN: **population**: A set of candidates developed in parallel across generations.
- EN: **fitness function**: A score saying how good a given solution is.
- EN: **black-box optimisation**: Searching for best settings when only the outcome, not the formula, is known.

## Subtopics (6 direct, 50 in total)

- [Budowa algorytmu ewolucyjnego: reprezentacja, operatory, parametry (Designing an evolutionary algorithm: representation, operators and parameters)](https://aiatlasgraph.com/t/evodesign.md): Components of an evolutionary algorithm: representation, initialisation, parent and survivor selection, variation operators, constraint handling, parameter control and sound comparison.
  - [Krzyżowanie: łączenie cech dwóch rodziców (Crossover (recombination) operators)](https://aiatlasgraph.com/t/evocrossover.md): Recombination operators building offspring from several parents' material, chosen to fit the representation: binary, real-valued or permutation.
  - [Mutacja: drobne losowe zmiany rozwiązania (Mutation operators)](https://aiatlasgraph.com/t/evomutation.md): Unary variation operators adding random perturbations to an individual; they provide exploration and reachability of the whole space.
  - [Nisze i utrzymywanie różnorodności populacji (Niching and diversity preservation)](https://aiatlasgraph.com/t/niching.md): Diversity-preserving techniques that let population-based metaheuristics locate multiple optima of a multimodal function in a single run.
  - [Obsługa ograniczeń w algorytmach ewolucyjnych (kary, naprawa) (Constraint handling in evolutionary algorithms)](https://aiatlasgraph.com/t/constrainthandling.md): Techniques for steering evolutionary search in constrained spaces: penalties, repair, feasibility rules, special operators and multi-objective formulations.
  - [Reprezentacja osobnika (kodowanie binarne, liczbowe, permutacje, drzewa) (Solution representation in evolutionary algorithms)](https://aiatlasgraph.com/t/evorepresentation.md): The genotype–phenotype mapping: choosing a data structure for candidates that defines the search space and admissible operators.
  - [Rzetelne porównywanie algorytmów optymalizacji (benchmarki) (Benchmarking evolutionary and black-box optimisers)](https://aiatlasgraph.com/t/evobenchmarking.md): Methodology for comparing black-box optimisers: standardised function suites, evaluation budgets, time-to-target measures and statistical tests.
    - [Krytyka „nowych” metaheurystyk opartych na metaforach (Critique of metaphor-based metaheuristics)](https://aiatlasgraph.com/t/metaphorcritique.md): A methodological strand showing many metaphor-based metaheuristics are renamed known techniques, and calling for description in standard optimisation terms.
  - [Selekcja rodziców i przeżycia (turniej, ruletka, elitaryzm) (Parent and survivor selection (tournament, roulette, elitism))](https://aiatlasgraph.com/t/evoselection.md): Mechanisms for choosing parents and survivors that control selection pressure: proportional, rank-based and tournament, plus replacement strategies and elitism.
  - [Strojenie i samoadaptacja parametrów algorytmu ewolucyjnego (Parameter tuning and control in evolutionary algorithms)](https://aiatlasgraph.com/t/parametercontrol.md): Parameter tuning (static choice before a run) and parameter control (deterministic, adaptive or self-adaptive changes during a run).
- [Ewolucja z modelami językowymi (LLM-guided evolutionary search)](https://aiatlasgraph.com/t/llmevolution.md): Methods where large language models act as variation operators in an evolutionary algorithm while an evaluator automatically scores programs, prompts or agents.
  - [Ewolucyjne odkrywanie algorytmów z LLM (LLM-driven program and algorithm evolution)](https://aiatlasgraph.com/t/llmprogramsearch.md): Evolutionary search over programs in which a language model generates code variants and an evaluator scores them on a mathematical or engineering task.
  - [Ewolucyjne ulepszanie poleceń dla modeli językowych (Evolutionary prompt optimisation)](https://aiatlasgraph.com/t/evoprompt.md): Optimising prompt text with an evolutionary algorithm where a language model performs mutation and crossover and selection uses validation scores.
  - [Model językowy jako operator krzyżowania i mutacji (Language models as evolutionary variation operators)](https://aiatlasgraph.com/t/llmoperators.md): Using a language model as the variation operator in an evolutionary algorithm: mutation by editing or crossover by prompting several parents.
  - [Samodoskonalące się agenty (ewolucja agentów) (Evolutionary self-improvement of agents)](https://aiatlasgraph.com/t/agentevolution.md): Evolutionary, archive-based search over agent designs where a foundation model edits agent code and benchmarks empirically validate changes.
- [Inteligencja roju (Swarm intelligence)](https://aiatlasgraph.com/t/swarmintel.md): Optimisation methods built on collective behaviour of many simple agents, mainly particle swarms and ant colony algorithms.
  - [Algorytmy mrówkowe (ACO) (Ant colony optimisation (ACO))](https://aiatlasgraph.com/t/aco.md): A metaheuristic for combinatorial problems where agents probabilistically build solutions guided by pheromone and heuristics, with pheromone reinforced and evaporated.
  - [Optymalizacja rojem cząstek (PSO) (Particle swarm optimisation (PSO))](https://aiatlasgraph.com/t/pso.md): A population metaheuristic in which particles update velocity from inertia, their personal best and their neighbourhood best.
  - [Robotyka rojowa (Swarm robotics)](https://aiatlasgraph.com/t/swarmrobotics.md): Designing collective behaviour for large groups of simple autonomous robots with local sensing and communication and no central control.
  - [Symulacja stada (boids) (Boids and flocking simulation)](https://aiatlasgraph.com/t/boids.md): A distributed flocking model where each agent steers by three rules relative to neighbours within a local range.
  - [Sztuczna kolonia pszczół (ABC) (Artificial bee colony algorithm (ABC))](https://aiatlasgraph.com/t/beecolony.md): A swarm metaheuristic with three bee roles — employed, onlooker and scout — for continuous optimisation.
- [Klasyczne algorytmy ewolucyjne (Classical evolutionary algorithms)](https://aiatlasgraph.com/t/evoclassic.md): The main evolutionary algorithm families: genetic algorithms, evolution strategies, genetic programming and evolutionary multi-objective optimisation.
  - [Algorytmy estymacji rozkładu (EDA) (Estimation of distribution algorithms (EDA))](https://aiatlasgraph.com/t/eda.md): Probabilistic model-building metaheuristics: they fit a distribution to selected good solutions and sample the next population from it.
  - [Algorytmy genetyczne (Genetic algorithms (GA))](https://aiatlasgraph.com/t/geneticalgorithms.md): A population algorithm encoding solutions as chromosomes and creating offspring through selection, crossover and mutation.
    - [Model wyspowy (równoległe populacje z migracją) (Island model and parallel evolutionary algorithms)](https://aiatlasgraph.com/t/islandmodel.md): Coarse-grained parallel evolution: independent subpopulations exchanging individuals according to a migration topology and schedule.
  - [Algorytmy memetyczne (ewolucja z lokalnym ulepszaniem) (Memetic algorithms)](https://aiatlasgraph.com/t/memeticalgorithms.md): An evolutionary algorithm with one or more local search phases inside its generational cycle.
  - [Ewolucja różnicowa (DE) (Differential evolution (DE))](https://aiatlasgraph.com/t/differentialevolution.md): A population method for continuous optimisation where a mutant is a base vector plus a scaled difference of two random members.
  - [Ewolucja wspomagana modelem zastępczym (gdy ocena jest droga) (Surrogate-assisted evolutionary optimisation)](https://aiatlasgraph.com/t/surrogateea.md): Evolutionary algorithms replacing some expensive objective evaluations with approximations from regression or classification models learned during the search.
  - [Ewolucyjna optymalizacja wielokryterialna (NSGA-II) (Evolutionary multi-objective optimisation (NSGA-II))](https://aiatlasgraph.com/t/multiobjectiveevo.md): Evolutionary algorithms approximating the Pareto front of a multi-objective problem in one run, such as NSGA-II, NSGA-III and MOEA/D.
    - [Optymalizacja przy wielu celach naraz (NSGA-III, MOEA/D) (Many-objective evolutionary optimisation (NSGA-III, MOEA/D))](https://aiatlasgraph.com/t/manyobjectiveevo.md): Evolutionary algorithms for problems with typically four or more objectives, built on reference points or decomposition into scalar subproblems.
    - [Wskaźnik hiperobjętości frontu Pareto (Hypervolume indicator for Pareto fronts)](https://aiatlasgraph.com/t/hypervolume.md): A quality indicator for a set of non-dominated solutions, measuring the objective-space volume dominated by that set relative to a reference point.
  - [Koewolucja: populacje oceniane przez wzajemne starcia (Coevolutionary algorithms)](https://aiatlasgraph.com/t/coevolution.md): Evolutionary algorithms in which at least part of the selection signal comes from interactions among individuals in one or more populations.
  - [Programowanie genetyczne i regresja symboliczna (Genetic programming and symbolic regression)](https://aiatlasgraph.com/t/geneticprogramming.md): Evolution of expression trees or programs; its main use is symbolic regression, discovering readable formulas from data.
    - [Ewolucja gramatyczna (programy budowane z reguł gramatyki) (Grammatical evolution)](https://aiatlasgraph.com/t/grammaticalevolution.md): Genetic programming with a genotype–phenotype mapping through a context-free grammar in BNF notation, evolving programs in an arbitrary language.
    - [Ewolucyjne ulepszanie i naprawa istniejącego kodu (Genetic improvement and automated program repair)](https://aiatlasgraph.com/t/geneticimprovement.md): Search, usually by genetic programming, over edits to existing code to repair bugs or improve performance.
    - [Kartezjańskie programowanie genetyczne (programy jako siatka węzłów) (Cartesian genetic programming (CGP))](https://aiatlasgraph.com/t/cartesiangp.md): Genetic programming encoded as a directed graph on a grid of nodes, with an integer genotype and inactive genes enabling neutral drift.
  - [Strategie ewolucyjne i CMA-ES (Evolution strategies and CMA-ES)](https://aiatlasgraph.com/t/evostrategies.md): Evolutionary continuous optimisers that sample candidates from a normal distribution and adapt its mean, step size and covariance matrix.
    - [Naturalne strategie ewolucyjne (NES) (Natural evolution strategies (NES))](https://aiatlasgraph.com/t/naturalES.md): Evolution strategies that update search-distribution parameters by the natural gradient of expected fitness.
  - [Uczące się systemy klasyfikatorów (ewolucja reguł „jeśli–to”) (Learning classifier systems (LCS))](https://aiatlasgraph.com/t/lcs.md): Rule-based learning systems combining a population of condition–action classifiers, reward-based credit assignment and a genetic algorithm discovering new rules.
- [Neuroewolucja (Neuroevolution)](https://aiatlasgraph.com/t/neuroevolution.md): Applying evolutionary algorithms to optimise weights, architectures, hyperparameters or learning rules of neural networks.
  - [Ewolucja budowy sieci (NEAT) (NeuroEvolution of Augmenting Topologies (NEAT))](https://aiatlasgraph.com/t/neat.md): An algorithm evolving network weights and topology together, using historical gene markings, speciation and gradual complexification from minimal structure.
    - [Ewolucja wzorów połączeń dużych sieci (HyperNEAT) (HyperNEAT and compositional pattern-producing networks)](https://aiatlasgraph.com/t/hyperneat.md): Neuroevolution with indirect encoding: NEAT evolves a CPPN that sets connection weights between neurons placed in geometric space.
  - [Ewolucyjne projektowanie architektur sieci (NAS) (Evolutionary neural architecture search)](https://aiatlasgraph.com/t/evonas.md): Searching neural architecture space with an evolutionary algorithm whose fitness is the quality of the trained candidate.
  - [Strategie ewolucyjne w trenowaniu sieci i LLM (Evolution strategies as an alternative to RL)](https://aiatlasgraph.com/t/esscale.md): Scalable evolution strategies estimating an improvement direction from scores of randomly perturbed parameter copies, used in RL and in fine-tuning large language models.
  - [Trenowanie populacyjne (Population Based Training) (Population Based Training (PBT))](https://aiatlasgraph.com/t/pbt.md): An asynchronous method jointly optimising weights and hyperparameters of a model population, discovering a hyperparameter schedule rather than one fixed setting.
- [Różnorodność i ewolucja otwarta (Quality diversity and open-endedness)](https://aiatlasgraph.com/t/qualitydiversity.md): Algorithms that illuminate a solution space with collections of diverse high-quality candidates, plus research on open-ended, never-ending generation of novelty.
  - [MAP-Elites: mapa najlepszych wariantów (MAP-Elites)](https://aiatlasgraph.com/t/mapelites.md): A quality-diversity algorithm keeping a grid of niches defined by behaviour features and the best solution in each niche.
  - [Poszukiwanie nowości (novelty search) (Novelty search)](https://aiatlasgraph.com/t/noveltysearch.md): An evolutionary algorithm replacing the objective with a behavioural novelty score relative to population and archive, effective on deceptive problems.
  - [Red teaming jako wyszukiwanie quality-diversity (Quality-diversity red teaming)](https://aiatlasgraph.com/t/qdredteaming.md): Generating diverse adversarial prompts as a quality-diversity problem: a MAP-Elites archive indexed by risk category and attack style.
  - [Systemy otwarte (open-endedness) (Open-ended learning systems)](https://aiatlasgraph.com/t/openendedness.md): Research on systems that endlessly generate novel, learnable artefacts or tasks along with their solutions.

## Sources

- [GECCO 2026 – program tracks (ACM SIGEVO)](<https://gecco-2026.sigevo.org/Tracks>) `gecco2026tracks` · by ACM SIGEVO
- [Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap](<https://arxiv.org/abs/2401.10034>) `evo-llm-survey-2024` · by Xingyu Wu, Sheng-hao Wu, Jibin Wu, Liang Feng, Kay Chen Tan
- [Designing neural networks through neuroevolution](<https://www.nature.com/articles/s42256-018-0006-z>) `neuroevolution-review-2019` · by Kenneth O. Stanley, Jeff Clune, Joel Lehman, Risto Miikkulainen

---

AI Atlas revision 122 (2026-10-30) · HTML: https://aiatlasgraph.com/t/evolutionary · index: https://aiatlasgraph.com/llms.txt · everything: https://aiatlasgraph.com/llms-full.txt · updated 2026-10-30