EALG: Evolutionary Adversarial Generation of Language Model-Guided Generators for Combinatorial Optimization

• URL: http://arxiv.org/abs/2506.02594v1
• Date: Tue, 03 Jun 2025 08:13:41 GMT
• Title: EALG: Evolutionary Adversarial Generation of Language Model-Guided Generators for Combinatorial Optimization
• Authors: Ruibo Duan, Yuxin Liu, Xinyao Dong, Chenglin Fan,
• Abstract summary: We introduce EALG (Evolutionary Adrial Generation of Language Model Generators), a novel framework that co-evolutione optimization problem instances and their corresponding solvers using large language models (LLMs)<n>EALG leverages a mutation-based approach that dynamically evolves instance generation procedures to create increasingly difficult problems, while simultaneously adaptive adversarial algorithms through interactions with LLMs guided by algorithmic structure.<n>This work explores a new paradigm for optimization that integrates instance generation with solver design, resulting in state-of-the-art performance.
• Score: 5.575239967310329
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating challenging instances is crucial for the evaluation and advancement of combinatorial optimization solvers. In this work, we introduce EALG (Evolutionary Adversarial Generation of Language Model-Guided Generators), a novel framework that automates the co-evolution of optimization problem instances and their corresponding heuristic solvers using large language models (LLMs). EALG leverages a mutation-based adversarial approach that dynamically evolves instance generation procedures to create increasingly difficult problems, while simultaneously synthesizing adaptive heuristic algorithms through interactions with LLMs guided by algorithmic structure. Unlike existing approaches that focus solely on static benchmark creation or manual solver design, EALG provides a seamless pipeline from instance generation to solver synthesis. Experimental results demonstrate that EALG generates significantly harder instances than current benchmarks, and its synthesized solvers generalize effectively across a broad spectrum of combinatorial tasks. This work explores a new paradigm for combinatorial optimization that integrates instance generation with solver design, resulting in state-of-the-art performance.

Related papers

• STRCMP: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization [18.162186876640764]
  Combinatorial optimization (CO) problems, central to operation research and theoretical computer science, present significant computational challenges due to their NP-hard nature.<n>We propose STRCMP, a novel structure-aware algorithm discovery framework that systematically integrates structure priors to enhance solution quality and solving efficiency.<n>Our framework combines a graph neural network (GNN) for extracting structural embeddings from CO instances with an LLM conditioned on these embeddings to identify high-performing algorithms in the form of solver-specific codes.
  arXiv  Detail & Related papers  (2025-05-22T15:37:42Z)
• CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design [11.639825726501659]
  Large language models (LLMs) can autonomously discover high-performings at a fraction of the traditional cost.<n>We propose a hybrid framework that combines verbal and numerical guidance.<n>Our method outperforms state-of-the-art (SOTA) baselines across various optimization tasks.
  arXiv  Detail & Related papers  (2025-05-18T07:48:47Z)
• Combinatorial Optimization via LLM-driven Iterated Fine-tuning [47.66752049943335]
  We present a novel way to integrate flexible, context-dependent constraints into optimization by leveraging Large Language Models (LLMs)<n>Our framework balances locally constraints with rigorous global optimization more effectively than baseline sampling methods.
  arXiv  Detail & Related papers  (2025-03-10T04:58:18Z)
• Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithms [3.833708891059351]
  Large Language Models (LLMs) and Evolutionary Algorithms (EAs) offer promising new approach to overcome limitations and make optimization more automated. LLMs act as dynamic agents that can generate, refine, and interpret optimization strategies. EAs efficiently explore complex solution spaces through evolutionary operators.
  arXiv  Detail & Related papers  (2024-10-28T09:04:49Z)
• Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach [4.442101733807905]
  This study proposes a new framework that combines a large language model (LLM) with traditional evolutionary algorithms to enhance the algorithm's search capability and generalization performance. We leverage an auxiliary evaluation function and automated prompt construction within the adaptive mechanism to flexibly adjust the utilization of the LLM.
  arXiv  Detail & Related papers  (2024-10-03T08:37:02Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Backpropagation of Unrolled Solvers with Folded Optimization [55.04219793298687]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. One typical strategy is algorithm unrolling, which relies on automatic differentiation through the operations of an iterative solver. This paper provides theoretical insights into the backward pass of unrolled optimization, leading to a system for generating efficiently solvable analytical models of backpropagation.
  arXiv  Detail & Related papers  (2023-01-28T01:50:42Z)
• A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences [55.25331349436895]
  Deep generative models have emerged as a popular machine learning-based approach for inverse problems in the life sciences. These problems often require sampling new designs that satisfy multiple properties of interest in addition to learning the data distribution.
  arXiv  Detail & Related papers  (2022-10-19T19:04:45Z)
• 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)
• EOS: a Parallel, Self-Adaptive, Multi-Population Evolutionary Algorithm for Constrained Global Optimization [68.8204255655161]
  EOS is a global optimization algorithm for constrained and unconstrained problems of real-valued variables. It implements a number of improvements to the well-known Differential Evolution (DE) algorithm. Results prove that EOSis capable of achieving increased performance compared to state-of-the-art single-population self-adaptive DE algorithms.
  arXiv  Detail & Related papers  (2020-07-09T10:19:22Z)

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.