Evolutionary Computation as Natural Generative AI

• URL: http://arxiv.org/abs/2510.08590v1
• Date: Sat, 04 Oct 2025 01:54:31 GMT
• Title: Evolutionary Computation as Natural Generative AI
• Abstract summary: Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity.<n>EC is a generative paradigm governed by exploratory search under natural selection.<n>We emphasize structured disruption and selection pressure moderation as essential drivers of creativity.
• Score: 35.99576885880116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits of available data. This work establishes a fundamental connection between EC and GenAI, redefining EC as Natural Generative AI (NatGenAI) -- a generative paradigm governed by exploratory search under natural selection. We demonstrate that classical EC with parent-centric operators mirrors conventional GenAI, while disruptive operators enable structured evolutionary leaps, often within just a few generations, to generate out-of-distribution artifacts. Moreover, the methods of evolutionary multitasking provide an unparalleled means of integrating disruptive EC (with cross-domain recombination of evolved features) and moderated selection mechanisms (allowing novel solutions to survive), thereby fostering sustained innovation. By reframing EC as NatGenAI, we emphasize structured disruption and selection pressure moderation as essential drivers of creativity. This perspective extends the generative paradigm beyond conventional boundaries and positions EC as crucial to advancing exploratory design, innovation, scientific discovery, and open-ended generation in the GenAI era.

Related papers

• Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection [2.2672499384619993]
  GenRes is a novel framework for generative residual learning via a neural tensor network.<n>GenRes++ employs a learnable attention mechanism to aggregate relational features across multiple transformed samples.<n>Experiments on multiple benchmark datasets demonstrate that the proposed GenRes++ approach outperforms existing methods.
  arXiv  Detail & Related papers  (2026-07-09T16:36:54Z)
• CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges [69.3795501613098]
  We introduce CreativeBench, a benchmark for evaluating machine creativity in code generation.<n>CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty.<n>We propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity.
  arXiv  Detail & Related papers  (2026-03-12T12:36:56Z)
• Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation [1.124958340749622]
  We propose a framework that includes a reproduction module, similar to natural species reproduction, balancing diversity and specialization.<n>By integrating RL, imitation learning (IL), and a coevolutionary agent-terrain curriculum, our system evolves agents continuously through complex tasks.<n>Our initial experiments show that this method improves exploration efficiency and supports open-ended learning.
  arXiv  Detail & Related papers  (2025-03-24T10:40:03Z)
• Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution [61.80716438091887]
  GenDiE (Generate, Discriminate, Evolve) is a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization.<n>By treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches.<n>Experiments on ASQA (in-domain LFQA) and ConFiQA datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness.
  arXiv  Detail & Related papers  (2025-03-03T16:08:33Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Neural Genetic Search in Discrete Spaces [14.666165546724159]
  We introduce a novel test-time search method, Neural Genetic Search (NGS)<n>NGS incorporates the evolutionary mechanism of genetic algorithms into the generation procedure of deep models.<n>This approach offers a versatile and easy-to-implement search algorithm for deep generative models.
  arXiv  Detail & Related papers  (2025-02-09T01:26:49Z)
• Generative midtended cognition and Artificial Intelligence. Thinging with thinging things [0.0]
  "generative midtended cognition" explores the integration of generative AI with human cognition. Term "generative" reflects AI's ability to iteratively produce structured outputs, while "midtended" captures the potential hybrid (human-AI) nature of the process.
  arXiv  Detail & Related papers  (2024-11-11T09:14:27Z)
• When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges [50.280704114978384]
  Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text.<n> Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems.
  arXiv  Detail & Related papers  (2024-01-19T05:58:30Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• A Neuro-mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization [55.11642177631929]
  Large neural generative models are capable of synthesizing semantically rich passages of text or producing complex images. We discuss the COGnitive Neural GENerative system, such an architecture that casts the Common Model of Cognition.
  arXiv  Detail & Related papers  (2023-10-14T23:28:48Z)
• Towards Large-Scale Simulations of Open-Ended Evolution in Continuous Cellular Automata [0.0]
  We build large-scale evolutionary simulations using parallel computing framework JAX. We report a number of system design choices, including implicit implementation of genetic operators. We propose several factors that may further facilitate open-ended evolution.
  arXiv  Detail & Related papers  (2023-04-12T06:40:11Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.