Saved in:
Bibliographic Details
Main Authors: Xu, Meng, Liu, Jiao, Ong, Yew Soon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912625770627072
author Xu, Meng
Liu, Jiao
Ong, Yew Soon
author_facet Xu, Meng
Liu, Jiao
Ong, Yew Soon
contents Genetic programming (GP) has demonstrated strong effectiveness in evolving tree-structured heuristics for complex optimization problems. Yet, in dynamic and large-scale scenarios, the most effective heuristics are often highly complex, hindering interpretability, slowing convergence, and limiting transferability across tasks. To address these challenges, we present EvoSpeak, a novel framework that integrates GP with large language models (LLMs) to enhance the efficiency, transparency, and adaptability of heuristic evolution. EvoSpeak learns from high-quality GP heuristics, extracts knowledge, and leverages this knowledge to (i) generate warm-start populations that accelerate convergence, (ii) translate opaque GP trees into concise natural-language explanations that foster interpretability and trust, and (iii) enable knowledge transfer and preference-aware heuristic generation across related tasks. We verify the effectiveness of EvoSpeak through extensive experiments on dynamic flexible job shop scheduling (DFJSS), under both single- and multi-objective formulations. The results demonstrate that EvoSpeak produces more effective heuristics, improves evolutionary efficiency, and delivers human-readable reports that enhance usability. By coupling the symbolic reasoning power of GP with the interpretative and generative strengths of LLMs, EvoSpeak advances the development of intelligent, transparent, and user-aligned heuristics for real-world optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02686
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EvoSpeak: Large Language Models for Interpretable Genetic Programming-Evolved Heuristics
Xu, Meng
Liu, Jiao
Ong, Yew Soon
Machine Learning
Genetic programming (GP) has demonstrated strong effectiveness in evolving tree-structured heuristics for complex optimization problems. Yet, in dynamic and large-scale scenarios, the most effective heuristics are often highly complex, hindering interpretability, slowing convergence, and limiting transferability across tasks. To address these challenges, we present EvoSpeak, a novel framework that integrates GP with large language models (LLMs) to enhance the efficiency, transparency, and adaptability of heuristic evolution. EvoSpeak learns from high-quality GP heuristics, extracts knowledge, and leverages this knowledge to (i) generate warm-start populations that accelerate convergence, (ii) translate opaque GP trees into concise natural-language explanations that foster interpretability and trust, and (iii) enable knowledge transfer and preference-aware heuristic generation across related tasks. We verify the effectiveness of EvoSpeak through extensive experiments on dynamic flexible job shop scheduling (DFJSS), under both single- and multi-objective formulations. The results demonstrate that EvoSpeak produces more effective heuristics, improves evolutionary efficiency, and delivers human-readable reports that enhance usability. By coupling the symbolic reasoning power of GP with the interpretative and generative strengths of LLMs, EvoSpeak advances the development of intelligent, transparent, and user-aligned heuristics for real-world optimization problems.
title EvoSpeak: Large Language Models for Interpretable Genetic Programming-Evolved Heuristics
topic Machine Learning
url https://arxiv.org/abs/2510.02686