用大模型自我反思优化提示词，自动设计更优启发式算法。
MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design
- 通过迭代优化生成启发式算法的提示词，而非直接修改代码。
- 在真实问题和基准测试中显著优于现有方法，提升算法性能。
- 适合对可解释性与自动化算法设计感兴趣的研究者。
本文提出MeLA，一种基于元认知的大语言模型驱动架构，开创了自动启发式设计（AHD）的新范式。传统进化方法直接操作启发式代码，而MeLA则演化用于指导大语言模型生成启发式的指令提示词。该“提示词进化”过程由新颖的元认知框架驱动，系统通过分析性能反馈，系统性地优化生成策略。MeLA架构包含问题分析器、错误诊断系统和元认知搜索引擎，分别负责构建初始策略提示、修复故障代码，并基于启发式有效性迭代优化提示词。在涵盖基准与真实问题的全面实验中，MeLA持续生成更有效且鲁棒的启发式算法，显著优于当前最先进方法。研究表明，以认知科学为蓝图构建AI架构具有深远潜力：通过使大语言模型具备元认知能力以调控其求解过程，我们能实现更稳健、可解释的自动启发式设计路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。