MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design

TL;DR

MeLA introduces a novel metacognitive framework that evolves prompts guiding LLMs to generate heuristics, significantly improving their effectiveness and robustness in solving complex problems.

Contribution

This work pioneers prompt evolution driven by metacognitive feedback within an LLM-based architecture for automatic heuristic design.

Findings

MeLA outperforms existing methods on benchmark problems.

The architecture produces more effective heuristics.

Metacognitive prompt refinement enhances heuristic robustness.

Abstract

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.