CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models
This addresses the challenge of improving heuristic generation in optimization for researchers in automated problem-solving, though it appears incremental as it builds on existing LLM-MCTS integration.
The paper tackles the problem of automatic heuristic design for complex optimization problems by proposing CogMCTS, a cognitive-guided Monte Carlo Tree Search framework that integrates large language models with multi-round feedback and dual-track expansion. The result shows that CogMCTS outperforms existing LLM-based methods in stability, efficiency, and solution quality.
Automatic Heuristic Design (AHD) is an effective1 framework for solving complex optimization prob-2 lems. The development of large language mod-3 els (LLMs) enables the automated generation of4 heuristics. Existing LLM-based evolutionary meth-5 ods rely on population strategies and are prone6 to local optima. Integrating LLMs with Monte7 Carlo Tree Search (MCTS) improves the trade-off8 between exploration and exploitation, but multi-9 round cognitive integration remains limited and10 search diversity is constrained. To overcome these11 limitations, this paper proposes a novel cognitive-12 guided MCTS framework (CogMCTS). CogMCTS13 tightly integrates the cognitive guidance mecha-14 nism of LLMs with MCTS to achieve efficient au-15 tomated heuristic optimization. The framework16 employs multi-round cognitive feedback to incor-17 porate historical experience, node information, and18 negative outcomes, dynamically improving heuris-19 tic generation. Dual-track node expansion com-20 bined with elite heuristic management balances the21 exploration of diverse heuristics and the exploita-22 tion of high-quality experience. In addition, strate-23 gic mutation modifies the heuristic forms and pa-24 rameters to further enhance the diversity of the so-25 lution and the overall optimization performance.26 The experimental results indicate that CogMCTS27 outperforms existing LLM-based AHD methods in28 stability, efficiency, and solution quality.