MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design

• URL: http://arxiv.org/abs/2606.14202v3
• Date: Wed, 17 Jun 2026 13:32:28 GMT
• Title: MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design
• Abstract summary: We propose MeEvo, a dual-layer Automatic Heuristic Design framework that cyclically couples Natural Evolution and Metacognitive Evolution.<n>MeEvo achieves stronger and more stable performance than existing LLM-based AHD architectures, especially on complex constrained tasks.
• Score: 17.812076497570157
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have advanced Automatic Heuristic Design (AHD) by enabling heuristic generation through reasoning and code synthesis. Existing LLM-based AHD architectures mainly follow two paradigms: Natural Evolution, which uses crossover and mutation to explore heuristic programs, and Metacognitive Evolution, which refines reasoning through reflection. However, Natural Evolution discards reasoning traces, weakening knowledge inheritance and exploitation, while Metacognitive Evolution lacks population-level recombination, limiting exploration and increasing the risk of premature convergence. These limitations reduce search efficiency, stability, and solution quality on complex problems. To address this gap, we propose MeEvo, a dual-layer AHD framework that cyclically couples Natural Evolution and Metacognitive Evolution. Natural Evolution explores heuristic code while recording reasoning traces, fitness values, and errors into a shared history; Metacognitive Evolution then reflects on this history to generate improved heuristics that re-enter the parent pool for the next cycle. This design enables population-driven exploration and reflection-driven refinement to reinforce each other. Experiments on five optimization problems with two LLM backbones show that MeEvo achieves stronger and more stable performance than existing LLM-based AHD architectures, especially on complex constrained tasks.

Related papers

• MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design [16.59846708454225]
  We propose a grid-based framework that adversarially co-evolves problem instances and specialist features inside a Quality-Diversity (QD) archive.<n>For each pair sampled from distant grid regions, an LLM-guided evolutionary loop generates discriminative instances.<n>A LLM then contrasts the two reflections to produce multi-directional insights that persist in those regions and guide crossover and mutation.
  arXiv  Detail & Related papers  (2026-07-31T04:22:17Z)
• MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation [51.824145170051516]
  MobEvolve is a self-evolving framework for human mobility generation.<n>It employs an agent to iteratively evolve its internal logic.<n>It significantly outperforms state-of-the-art deep generative and LLM-based methods.
  arXiv  Detail & Related papers  (2026-06-01T03:46:25Z)
• CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad [72.197582948888]
  We develop CausalEvolve, equipped with a causal scratchpad that leverages Large Language Models (LLMs) to identify and reason about guiding factors for evolution.<n>CaulEvolve first identifies outcome-level factors that offer complementary inspirations in improving the target objective.<n>During the evolution, CausalEvolve also inspects surprise patterns during the evolution and abductive reasoning to hypothesize new factors, which in turn offer novel directions.
  arXiv  Detail & Related papers  (2026-03-15T19:53:31Z)
• Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants [85.33837131101342]
  We propose a strategic roadmap organized into four pillars: foundational infrastructure, algorithmic optimization, cognitive reasoning, and unified multimodal intelligence.<n>We argue that this transition is essential for developing next-generation AI capable of complex structural reasoning, dynamic self-correction, and seamless multimodal integration.
  arXiv  Detail & Related papers  (2026-01-20T14:58:23Z)
• Cognitive Alpha Mining via LLM-Driven Code-Based Evolution [29.71597480304934]
  We introduce the Cognitive Alpha Mining Framework (CogAlpha), which combines code-level alpha representation with LLM-driven reasoning and evolutionary search.<n>Treating LLMs as adaptive cognitive agents, our framework iteratively refines, mutates, and recombines alpha candidates through prompts and financial feedback.<n>Experiments on A-share equities demonstrate that CogAlpha consistently discovers alphas with superior predictive accuracy, robustness, and generalization over existing methods.
  arXiv  Detail & Related papers  (2025-11-24T07:45:59Z)
• CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning [63.44477226386808]
  Chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks.<n>But it struggles in scientific domains where even advanced models often produce incorrect or superficial reasoning.<n>We propose CoT-Evo, an evolutionary CoT distillation framework to overcome this problem.
  arXiv  Detail & Related papers  (2025-10-15T05:29:56Z)
• Towards Understanding How Knowledge Evolves in Large Vision-Language Models [55.82918299608732]
  We investigate how multimodal knowledge evolves and eventually induces natural languages in Large Vision-Language Models (LVLMs)<n>We identify two key nodes in knowledge evolution: the critical layers and the mutation layers, dividing the evolution process into three stages: rapid evolution, stabilization, and mutation.<n>Our research is the first to reveal the trajectory of knowledge evolution in LVLMs, providing a fresh perspective for understanding their underlying mechanisms.
  arXiv  Detail & Related papers  (2025-03-31T17:35:37Z)
• A Survey on Self-Evolution of Large Language Models [116.54238664264928]
  Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. To address this issue, self-evolution approaches that enable LLMs to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
  arXiv  Detail & Related papers  (2024-04-22T17:43:23Z)
• ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution [35.39046514910755]
  This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics, featuring minimal manual intervention and open-ended spaces. To empower LHHs, we presentive Evolution (ReEvo), a novel integration of evolutionary search for efficiently exploring the white space, and reflections to provide verbal gradients within the space.
  arXiv  Detail & Related papers  (2024-02-02T05:04:51Z)
• When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges [50.280704114978384]
  Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text.<n> Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems.
  arXiv  Detail & Related papers  (2024-01-19T05:58:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.