CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design

• URL: http://arxiv.org/abs/2505.12285v1
• Date: Sun, 18 May 2025 07:48:47 GMT
• Title: CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design
• Authors: Ziyao Huang, Weiwei Wu, Kui Wu, Jianping Wang, Wei-Bin Lee,
• Abstract summary: 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.
• Score: 11.639825726501659
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed evolutionary search frameworks, can autonomously discover high-performing heuristics at a fraction of the traditional cost. However, existing approaches predominantly rely on verbal guidance, i.e., manipulating the prompt generation process, to steer the evolution of heuristics, without adapting the underlying LLM. We propose a hybrid framework that combines verbal and numerical guidance, the latter achieved by fine-tuning the LLM via reinforcement learning based on the quality of generated heuristics. This joint optimization allows the LLM to co-evolve with the search process. Our method outperforms state-of-the-art (SOTA) baselines across various optimization tasks, running locally on a single 24GB GPU using a 7B model with INT4 quantization. It surpasses methods that rely solely on verbal guidance, even when those use significantly more powerful API-based models.

Related papers

• Pareto-Grid-Guided Large Language Models for Fast and High-Quality Heuristics Design in Multi-Objective Combinatorial Optimization [3.952819864255911]
  Multi-objective optimization problems (MOCOP) frequently arise in practical applications that require the simultaneous optimization of conflicting objectives.<n>We introduce Multi-heuristics for MOCOP via Pareto-Grid-guided Evolution of LLMs (MPaGE)<n>MPaGE utilizes LLMs to prioritize with semantically distinct logical structures during variation, thus promoting diversity and mitigating redundancy within the population.
  arXiv  Detail & Related papers  (2025-07-28T15:26:43Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective [65.12150411762273]
  We show that pruning random demonstrations into seemingly incoherent "gibberish" can remarkably improve performance across diverse tasks.<n>We propose a self-discover prompt optimization framework, PromptQuine, that automatically searches for the pruning strategy by itself using only low-data regimes.
  arXiv  Detail & Related papers  (2025-06-22T07:53:07Z)
• Large Language Models for Design Structure Matrix Optimization [4.513609458468522]
  In complex engineering systems, the interdependencies among components or development activities are often modeled and analyzed using Design Structure Matrix (DSM)<n>Reorganizing elements within a DSM to minimize feedback loops and enhance modularity or process efficiency constitutes a challenging optimization problem in engineering design and operations.<n>In this study, we explore the potential of Large Language Models (LLMs) for helping solve such CO problems by leveraging their capabilities for advanced reasoning and contextual understanding.
  arXiv  Detail & Related papers  (2025-06-11T13:53:35Z)
• Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization [14.919482411153185]
  Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling optimization problems.<n>Existing approaches often rely on manually predefined evolutionary generalizations and single-task training schemes.<n>We propose Meta-Optimization of Heuristics (MoH), a novel framework that operates at the level of meta-learning.
  arXiv  Detail & Related papers  (2025-05-27T08:26:27Z)
• FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities [76.46448367752944]
  multimodal large language models (MLLMs) unify visual understanding and image generation within a single framework.<n>Most existing MLLMs rely on autore (AR) architectures, which impose inherent limitations on future development.<n>We introduce FUDOKI, a unified multimodal model purely based on discrete flow matching.
  arXiv  Detail & Related papers  (2025-05-26T15:46:53Z)
• GAAPO: Genetic Algorithmic Applied to Prompt Optimization [0.0]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, with their performance heavily dependent on the quality of input prompts.<n>While prompt engineering has proven effective, it typically relies on manual adjustments, making it time-consuming and potentially suboptimal.<n>This paper introducesGenetic Algorithm Applied to Prompt Optimization, a novel hybrid optimization framework that leverages genetic principles to evolve prompts through successive generations.
  arXiv  Detail & Related papers  (2025-04-09T11:19:42Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [86.21199607040147]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation language models.<n>We introduce Chain-of-Description, a step-by-step visual understanding method, and integrate structured chain-of-thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Extensive experiments demonstrate that SIcog produces next-generation foundation MLLMs with substantially improved multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution [39.42526347710991]
  Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization.<n>We introduce an end-to-end algorithm generation and optimization framework based on LLMs.<n>Our approach utilizes the deep semantic understanding of LLMs to convert natural language requirements or human-authored papers into code solutions.
  arXiv  Detail & Related papers  (2025-03-13T08:26:18Z)
• Leveraging Large Language Models to Develop Heuristics for Emerging Optimization Problems [0.0]
  Combinatorial optimization problems often rely on algorithms to generate efficient solutions.<n>Recent advances in artificial intelligence have demonstrated the potential to automate generation through evolutionary frameworks.<n>We propose the Contextual Evolution of Heuristics framework, which incorporates problem-specific descriptions to enhance in-context learning.
  arXiv  Detail & Related papers  (2025-03-05T10:22:49Z)
• Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems? [8.082897040940447]
  Large Language Models (LLMs) have shown strong capabilities in language understanding and reasoning across diverse domains.<n>In this work, we propose a systematic framework to evaluate the capability of LLMs to engage with problem structures.<n>We adopt the commonly used evolutionary (EVO) and propose a comprehensive evaluation framework that rigorously assesses the output fidelity of LLM-based operators.
  arXiv  Detail & Related papers  (2025-01-25T05:19:19Z)
• 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)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Enhancing Model Performance: Another Approach to Vision-Language Instruction Tuning [0.0]
  The integration of large language models (LLMs) with vision-language (VL) tasks has been a transformative development in the realm of artificial intelligence. We present a novel approach, termed Bottleneck Adapter, specifically crafted for enhancing the multimodal functionalities of these complex models. Our approach utilizes lightweight adapters to connect the image encoder and LLM without the need for large, complex neural networks.
  arXiv  Detail & Related papers  (2024-07-25T06:59:15Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Large Language Models to Enhance Bayesian Optimization [57.474613739645605]
  We present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within Bayesian optimization. At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations. Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse.
  arXiv  Detail & Related papers  (2024-02-06T11:44:06Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers [67.64162164254809]
  EvoPrompt is a framework for discrete prompt optimization.<n>It borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence.<n>It significantly outperforms human-engineered prompts and existing methods for automatic prompt generation.
  arXiv  Detail & Related papers  (2023-09-15T16:50:09Z)

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.