用遗传编程演化的启发式知识指导大语言模型解决动态多模式项目调度问题

中文摘要 AI 辅助

在动态多模式项目调度中，活动具有可选执行模式和不确定持续时间，且 precedence 关系与有限资源约束其执行。启发式优先级规则支持快速在线决策，但设计需大量领域专业知识。遗传编程（GP）超启发式算法可自动演化此类规则，而大语言模型（LLM）为调度信息解读与决策解释提供灵活接口。然而，零样本 LLM 决策可能缺乏领域知识、消耗大量 token 且重复查询间存在差异。因此，GP 演化规则可成为指导 LLM 决策的调度知识潜在来源。与现有 LLM-GP 混合模型（用 LLM 支持启发式演化）不同，本研究反向转移知识，即从高质量 GP 规则提取知识以指导在线 LLM 决策者。我们从高质量 GP 规则中提取知识，并通过特征选择（Feature Selection）、特征提示（Feature Hint）、规则参考（Rule Reference）和规则遵循（Rule Follow）机制注入知识。这些机制在调度性能、token 消耗、决策稳定性及生成理由中表达的特征关注点方面接受评估。GP 衍生的指导通常可提升无指导 LLM 的表现，但其表示方式至关重要：简化决策上下文或提供显式决策逻辑比突出重要特征更有效。特征选择实现最佳 token 效率，而规则遵循在 token 成本较高时达到强性能。指导还可提升决策稳定性并改变生成理由中表达的特征。

英文摘要

In dynamic multi-mode project scheduling, activities have alternative execution modes and uncertain durations, while precedence relations and limited resources constrain their execution. Heuristic priority rules support fast online decisions, but their design requires substantial domain expertise. Genetic programming (GP) hyper-heuristics can automatically evolve such rules. Large language models (LLMs), meanwhile, provide a flexible interface for interpreting scheduling information and explaining decisions. However, zero-shot LLM decisions may lack domain knowledge, consume many tokens, and vary across repeated queries. GP-evolved rules therefore provide a potential source of scheduling knowledge for guiding LLM decisions. Unlike existing LLM--GP hybrids that use LLMs to support heuristic evolution, we transfer knowledge in the reverse direction, using knowledge extracted from high-quality GP rules to guide an online LLM decision maker. We extract knowledge from high-quality GP rules and inject it through Feature Selection, Feature Hint, Rule Reference, and Rule Follow. These mechanisms are evaluated in terms of scheduling performance, token consumption, decision stability, and the feature focus expressed in generated rationales. GP-derived guidance generally improves the unguided LLM, but its representation matters. Simplifying the decision context or supplying explicit decision logic is more effective than highlighting important features. Feature Selection offers the best token efficiency, whereas Rule Follow achieves strong performance at greater token cost. Guidance also improves decision stability and changes the features expressed in generated rationales.

发表机构

• Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）
• School of Engineering and Computer Science（工程与计算机科学学院）
• Victoria University of Wellington（惠灵顿维多利亚大学）

机构由 AI 辅助整理，请以论文原文为准。