Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms

• URL: http://arxiv.org/abs/2412.03250v1
• Date: Wed, 04 Dec 2024 11:49:22 GMT
• Title: Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms
• Abstract summary: This paper introduces a novel approach to mutation control within evolutionary frameworks, inspired by theory of genetic algorithms.<n>We propose dynamic mutation prompts that adaptively regulate mutation rates, leveraging a heavy-tailed power-law distribution to balance exploration and exploitation.<n>Experiments show that the introduction of these dynamic rates can improve the convergence speed and adaptability of LLaMEA.
• Score: 2.2485774453793037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of Large Language Models (LLMs) with evolutionary computation (EC) has introduced a promising paradigm for automating the design of metaheuristic algorithms. However, existing frameworks, such as the Large Language Model Evolutionary Algorithm (LLaMEA), often lack precise control over mutation mechanisms, leading to inefficiencies in solution space exploration and potentially suboptimal convergence. This paper introduces a novel approach to mutation control within LLM-driven evolutionary frameworks, inspired by theory of genetic algorithms. Specifically, we propose dynamic mutation prompts that adaptively regulate mutation rates, leveraging a heavy-tailed power-law distribution to balance exploration and exploitation. Experiments using GPT-3.5-turbo and GPT-4o models demonstrate that GPT-3.5-turbo fails to adhere to the specific mutation instructions, while GPT-4o is able to adapt its mutation based on the prompt engineered dynamic prompts. Further experiments show that the introduction of these dynamic rates can improve the convergence speed and adaptability of LLaMEA, when using GPT-4o. This work sets the starting point for better controlled LLM-based mutations in code optimization tasks, paving the way for further advancements in automated metaheuristic design.

Related papers

• FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations [66.32852384262038]
  Mixed-integer programming (MIP) lies at the core of operations research and industrial optimization.<n>We propose FormuEvo, an evolutionary framework for automated discovery of solver-efficient MIP formulations.<n>FormuEvo frames MIP formulation design as evolutionary optimization over the symbolic space of MIP formulations.
  arXiv  Detail & Related papers  (2026-08-24T15:01:28Z)
• Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models [9.216325369400606]
  We extend the state-of-the-art FlowRepair approach by replacing a subset of its mutation operators with Large Language Models (LLMs)<n>Contrary to expectations, the LLM-based mutation substantially degrades repair performance under the FlowRepair experimental setup.<n>Our analysis reveals that, in this integration, LLMs struggle with precise symbolic edits, lack behavioral feedback, and generate a noisy search space.
  arXiv  Detail & Related papers  (2026-08-19T18:09:54Z)
• Towards A Generative Protein Evolution Machine with DPLM-Evo [73.57855006698269]
  We present DPLM-Evo, an evolutionary discrete diffusion framework that explicitly predicts substitution, insertion, and deletion operations during denoising.<n> DPLM-Evo improves sequence understanding and state-of-the-art mutation effect prediction performance on ProteinGym in the single-sequence setting.
  arXiv  Detail & Related papers  (2026-04-30T19:59:07Z)
• BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design [49.50107918295052]
  Large Language Model-based Hyper Heuristic (LHH) has recently emerged as an efficient way for automatic design.<n>We propose textbfBEAM (Bi-level Memory-adaptive Algorithmic Evolution) to address this problem.<n>We show that BEAM significantly outperforms existing LHHs, notably reducing the optimality gap by 37.84% on aggregate.
  arXiv  Detail & Related papers  (2026-04-14T15:46:47Z)
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Continuous Program Search [4.198653054660764]
  We frame this as an operator-design problem: learn a continuous program space where latent distance has behavioral meaning, then design mutation operators that exploit this structure without changing the evolutionary algorithm.<n>We make locality measurable by tracking action-level divergence under controlled latent perturbations, identifying an empirical trust region for behavior-local continuous variation.<n>Although isotropic mutation occasionally attains higher peak performance, geometry-compiled mutation yields faster, more reliable progress, demonstrating that semantically aligned mutation can substantially improve search efficiency without modifying the underlying evolutionary algorithm.
  arXiv  Detail & Related papers  (2026-02-07T18:41:14Z)
• Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations [55.047454145941366]
  Streaming Merging is an innovative model updating paradigm that conceptualizes merging as an iterative optimization process.<n> ARM is a strategy designed to approximate gradient descent dynamics.<n> ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model.
  arXiv  Detail & Related papers  (2026-02-03T08:15:57Z)
• LLM4EO: Large Language Model for Evolutionary Optimization in Flexible Job Shop Scheduling [4.782301990330074]
  This work leverages Large Language Models (LLMs) to perceive evolutionary dynamics and enable operator-level meta-evolution.<n>The proposed framework, LLM4EO, comprises three components: knowledge-transfer-based operator design, evolution perception and analysis, and adaptive operator evolution.
  arXiv  Detail & Related papers  (2025-11-20T15:56:09Z)
• LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization [54.35609820607923]
  Large language models (LLMs) offer new opportunities for assisting with algorithm design.<n>We propose LLM4CMO, a novel CMOEA based on a dual-population, two-stage framework.<n>LLMs can serve as efficient co-designers in the development of complex evolutionary optimization algorithms.
  arXiv  Detail & Related papers  (2025-08-16T02:00:57Z)
• GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters [61.51810815162003]
  We propose an SE(3)-equivariant adapter framework ( GeoAda) that enables flexible and parameter-efficient fine-tuning for controlled generative tasks.<n>GeoAda preserves the model's geometric consistency while mitigating overfitting and catastrophic forgetting.<n>We demonstrate the wide applicability of GeoAda across diverse geometric control types, including frame control, global control, subgraph control, and a broad range of application domains.
  arXiv  Detail & Related papers  (2025-07-02T18:44:03Z)
• Reparameterized LLM Training via Orthogonal Equivalence Transformation [54.80172809738605]
  We present POET, a novel training algorithm that uses Orthogonal Equivalence Transformation to optimize neurons.<n>POET can stably optimize the objective function with improved generalization.<n>We develop efficient approximations that make POET flexible and scalable for training large-scale neural networks.
  arXiv  Detail & Related papers  (2025-06-09T17:59:34Z)
• Regulatory DNA sequence Design with Reinforcement Learning [56.20290878358356]
  We propose a generative approach that leverages reinforcement learning to fine-tune a pre-trained autoregressive model. We evaluate our method on promoter design tasks in two yeast media conditions and enhancer design tasks for three human cell types.
  arXiv  Detail & Related papers  (2025-03-11T02:33:33Z)
• ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization [6.900025190052277]
  We introduce ControllableGPT, a controllable training framework for large language models. It is inspired by the biological processes of growth and evolution, which involve the expansion, shrinking, and mutation of sequences. It enables the precise management of specific locations and ranges within a sequence, while maintaining the integrity of any specified positions or subsequences.
  arXiv  Detail & Related papers  (2025-02-15T01:49:35Z)
• A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer [53.85265022754878]
  We propose a lightweight DDG predictor (Light-DDG) for fast mutation screening. We also release a large-scale dataset containing millions of mutation data for pre-training Light-DDG. For the target antibody, we propose a novel Mutation Explainer to learn mutation preferences.
  arXiv  Detail & Related papers  (2025-02-10T09:26:57Z)
• Preparing Spin Squeezed States via Adaptive Genetic Algorithm [9.168152138847445]
  We introduce a novel strategy employing an adaptive genetic algorithm (GA) for iterative optimization of control sequences to generate quantum nonclassical states. Inspired by Darwinian evolution, the algorithm iteratively refines control sequences using crossover, mutation, and elimination strategies. Our approach, compared to constant control schemes, yields a variety of control sequences capable of maintaining squeezing for the collective spin model.
  arXiv  Detail & Related papers  (2024-10-20T12:15:11Z)
• LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics [0.023020018305241332]
  This paper introduces a novel Large Language Model Evolutionary Algorithm (LLaMEA) framework. Given a set of criteria and a task definition (the search space), LLaMEA iteratively generates, mutates and selects algorithms. We show how this framework can be used to generate novel black-box metaheuristic optimization algorithms automatically.
  arXiv  Detail & Related papers  (2024-05-30T15:10:59Z)
• LLM Guided Evolution - The Automation of Models Advancing Models [0.0]
  "Guided Evolution" (GE) is a novel framework that diverges from traditional machine learning approaches. "Evolution of Thought" (EoT) enhances GE by enabling LLMs to reflect on and learn from the outcomes of previous mutations. Our application of GE in evolving the ExquisiteNetV2 model demonstrates its efficacy.
  arXiv  Detail & Related papers  (2024-03-18T03:44:55Z)
• Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies [47.129504708849446]
  Large Language Models (LLMs) have revolutionized the field of Natural Language Processing. LLMs lack systematic generalization, which allows to extrapolate the learned statistical regularities outside the training distribution. In this work, we offer a systematic benchmarking of GPT-4, one of the most advanced LLMs available.
  arXiv  Detail & Related papers  (2024-02-27T10:44:52Z)
• Genetic Algorithm enhanced by Deep Reinforcement Learning in parent selection mechanism and mutation : Minimizing makespan in permutation flow shop scheduling problems [0.18846515534317265]
  The proposed RL+GA method was specifically tested on the flow shop scheduling problem (FSP) The hybrid algorithm incorporates neural networks (NN) and uses the off-policy method Q-learning. Results of the study highlight the effectiveness of the RL+GA approach in improving the performance of the primitive GA.
  arXiv  Detail & Related papers  (2023-11-10T08:51:42Z)
• Towards Self-adaptive Mutation in Evolutionary Multi-Objective Algorithms [10.609857097723266]
  We study how self-adaptation influences multi-objective evolutionary algorithms. We show that adapting the mutation rate based on single-objective optimization and hypervolume can speed up the convergence of GSEMO. We propose a GSEMO with self-adaptive mutation, which considers optimizing for single objectives and adjusts the mutation rate for each solution individually.
  arXiv  Detail & Related papers  (2023-03-08T14:26:46Z)
• Manifold Gaussian Variational Bayes on the Precision Matrix [70.44024861252554]
  We propose an optimization algorithm for Variational Inference (VI) in complex models. We develop an efficient algorithm for Gaussian Variational Inference whose updates satisfy the positive definite constraint on the variational covariance matrix. Due to its black-box nature, MGVBP stands as a ready-to-use solution for VI in complex models.
  arXiv  Detail & Related papers  (2022-10-26T10:12:31Z)
• Effective Mutation Rate Adaptation through Group Elite Selection [50.88204196504888]
  This paper introduces the Group Elite Selection of Mutation Rates (GESMR) algorithm. GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions. With the same number of function evaluations and with almost no overhead, GESMR converges faster and to better solutions than previous approaches.
  arXiv  Detail & Related papers  (2022-04-11T01:08:26Z)
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design [55.41644538483948]
  We develop an easy-to-directed, scalable, and robust evolutionary greedy algorithm (AdaLead) AdaLead is a remarkably strong benchmark that out-competes more complex state of the art approaches in a variety of biologically motivated sequence design challenges.
  arXiv  Detail & Related papers  (2020-10-05T16:40:38Z)

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.