MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design
This addresses the challenge of designing effective heuristics automatically, offering a new paradigm that could impact AI and optimization domains, though it appears incremental in combining existing concepts like LLMs and metacognition.
The paper tackles the problem of automatic heuristic design by introducing MeLA, a metacognitive LLM-driven architecture that evolves prompts to guide LLMs in generating heuristics, resulting in consistently more effective and robust heuristics that significantly outperform state-of-the-art methods in experiments.
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.