LLMize: 一种基于大语言模型的数值优化框架
LLMize: A Framework for Large Language Model-Based Numerical Optimization
AI总结:
LLMize是一种基于大语言模型的数值优化框架,通过自然语言描述注入约束和领域知识,适用于复杂领域特定任务的优化。
摘要:
大语言模型(LLMs)最近在传统语言任务之外展示了强大的推理能力,这促使它们被用于数值优化。本文提出了LLMize,一个开源的Python框架,通过迭代提示和上下文学习使LLM驱动的优化成为可能。LLMize将优化视为一个黑箱过程,在其中候选解决方案以自然语言生成,通过外部目标函数进行评估,并在后续迭代中通过解决方案评分反馈进行优化。该框架支持多种优化策略,包括通过提示进行优化(OPRO)以及受进化算法和模拟退火启发的混合LLM方法。LLMize的一个关键优势是能够通过自然语言描述直接注入约束、规则和领域知识,使从业者能够在不需数学规划或元启发式设计专业知识的情况下定义复杂的优化问题。LLMize在凸优化、线性规划、旅行商问题、神经网络超参数调优和核燃料晶格优化上进行了评估。结果表明,尽管LLM驱动的优化在简单问题上不具竞争力,但为复杂、领域特定的任务提供了实用且易于访问的方法,这些任务中的约束和启发式方法难以形式化。
英文摘要:
Large language models (LLMs) have recently shown strong reasoning capabilities beyond traditional language tasks, motivating their use for numerical optimization. This paper presents LLMize, an open-source Python framework that enables LLM-driven optimization through iterative prompting and in-context learning. LLMize formulates optimization as a black-box process in which candidate solutions are generated in natural language, evaluated by an external objective function, and refined over successive iterations using solution-score feedback. The framework supports multiple optimization strategies, including Optimization by Prompting (OPRO) and hybrid LLM-based methods inspired by evolutionary algorithms and simulated annealing. A key advantage of LLMize is the ability to inject constraints, rules, and domain knowledge directly through natural language descriptions, allowing practitioners to define complex optimization problems without requiring expertise in mathematical programming or metaheuristic design. LLMize is evaluated on convex optimization, linear programming, the Traveling Salesman Problem, neural network hyperparameter tuning, and nuclear fuel lattice optimization. Results show that while LLM-based optimization is not competitive with classical solvers for simple problems, it provides a practical and accessible approach for complex, domain-specific tasks where constraints and heuristics are difficult to formalize.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。