MeLA：一种由元认知大语言模型驱动的自动启发式设计架构
MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design
AI总结：
本研究提出元认知LLM驱动的MeLA架构，通过进化引导LLM生成启发式的指令提示实现自动启发式设计，在多类实验中性能显著优于现有方法，为AHD提供了更鲁棒可解释的新路径。
摘要：
本文提出了MeLA——一种由元认知大语言模型（LLM）驱动的架构，为自动启发式设计（Automatic Heuristic Design, AHD）提供了全新范式。传统进化方法直接对启发式代码进行操作；与之不同，MeLA通过进化用于引导LLM生成这些启发式的指令提示来实现设计。这一“提示进化”过程由一种新颖的元认知框架驱动，系统会分析性能反馈，系统性地优化其生成策略。MeLA的架构整合了三大模块：用于构建初始策略提示的问题分析器、用于修复错误代码的错误诊断系统，以及基于启发式有效性迭代优化提示的元认知搜索引擎。在涵盖基准问题和现实问题的综合实验中，MeLA始终能生成更有效、更鲁棒的启发式，性能显著优于当前最优方法。最终，本研究证明了以认知科学为蓝图构建AI架构的巨大潜力，表明通过让LLM以元认知方式调控其问题解决过程，我们能为AHD开辟一条更鲁棒、更具可解释性的路径。
英文摘要：
This paper introduces MeLA, a Metacognitive LLM-Driven Architecture that presents a new paradigm for Automatic Heuristic Design (AHD). Traditional evolutionary methods operate directly on heuristic code; in contrast, MeLA evolves the instructional prompts used to guide a Large Language Model (LLM) in generating these heuristics. This process of "prompt evolution" is driven by a novel metacognitive framework where the system analyzes performance feedback to systematically refine its generative strategy. MeLA's architecture integrates a problem analyzer to construct an initial strategic prompt, an error diagnosis system to repair faulty code, and a metacognitive search engine that iteratively optimizes the prompt based on heuristic effectiveness. In comprehensive experiments across both benchmark and real-world problems, MeLA consistently generates more effective and robust heuristics, significantly outperforming state-of-the-art methods. Ultimately, this research demonstrates the profound potential of using cognitive science as a blueprint for AI architecture, revealing that by enabling an LLM to metacognitively regulate its problem-solving process, we unlock a more robust and interpretable path to AHD.
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。
