While Monte Carlo Tree Search (MCTS) shows promise in Large Language Model (LLM) based Automatic Heuristic Design (AHD), it suffers from a critical over-exploitation tendency under the limited computational budgets required for heuristic evaluation. To address this limitation, we propose Clade-AHD, an efficient framework that replaces node-level point estimates with clade-level Bayesian beliefs. By aggregating descendant evaluations into Beta distributions and performing Thompson Sampling over these beliefs, Clade-AHD explicitly models uncertainty to guide exploration, enabling more reliable decision-making under sparse and noisy evaluations. Extensive experiments on complex combinatorial optimization problems demonstrate that Clade-AHD consistently outperforms state-of-the-art methods while significantly reducing computational cost. The source code is publicly available at: https://github.com/Mriya0306/Clade-AHD.
@article{arxiv.2602.00549,
title = {Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design},
author = {Kezhao Lai and Yutao Lai and Hai-Lin Liu},
journal= {arXiv preprint arXiv:2602.00549},
year = {2026}
}