EvoSpeak: Large Language Models for Interpretable Genetic Programming-Evolved Heuristics
This work addresses the need for interpretable and efficient heuristics in real-world optimization problems, offering an incremental improvement by combining existing GP and LLM techniques.
The paper tackles the problem of complex and opaque heuristics evolved by genetic programming (GP) in dynamic optimization scenarios, presenting EvoSpeak, a framework that integrates GP with large language models (LLMs) to improve efficiency, interpretability, and adaptability, with results showing more effective heuristics and enhanced usability in experiments on dynamic flexible job shop scheduling.
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.