合成特征提取器：一种用于算法选择的智能体方法

中文摘要 AI 辅助

约束满足问题的算法选择需要提取能捕捉问题结构的特征，手动设计特征提取器需要深厚的领域专业知识，且当出现新的问题类别时很快会成为瓶颈。本文提出一种自动化方法，该方法使用大语言模型（LLMs）构建智能体的检查-修复-验证循环，以合成可执行的Python脚本，作为可解释的、特定问题的特征提取器。给定高级MiniZinc模型和一个实例，LLM智能体生成代码来构建类型化图表示，并计算图密度、变量聚类和约束紧密度等结构属性。我们在三个组合问题（车辆路径、汽车排序、固定长度纠错码）上，使用由五个最先进求解器组成的组合体对我们的方法进行评估。合成的提取器产生的算法选择器，在测试集准确率上始终优于专家精心设计的mzn2feat特征（在FLECC上最高达8.3个百分点（pp））和最佳的基于Transformer的trans2feat变体，同时合成的特征提取器保持可检查性。

英文摘要

Algorithm selection for constraint satisfaction problems requires extracting features that capture problem structure. Manually designing feature extractors demands deep domain expertise and quickly becomes a bottleneck when new problem classes appear. We present an automated approach that uses Large Language Models (LLMs) in an agentic check--fix--verify loop to synthesize executable Python scripts that act as interpretable, problem-specific feature extractors. Given a high-level MiniZinc model and an instance, the LLM agent generates code that constructs a typed graph representation and computes structural properties such as graph density, variable clustering, and constraint tightness. We evaluate our approach on three combinatorial problems (vehicle routing, car sequencing, fixed-length error-correcting codes) with a portfolio of five state-of-the-art solvers. The synthesized extractors yield algorithm selectors that consistently outperform both expert-curated mzn2feat features (up to $8.3$ percentage points (pp) test-set accuracy on FLECC) and the best transformer-based trans2feat variants. In the meanwhile, the synthesized feature extractors remain inspectable.

发表机构

• TU Wien（维也纳技术大学）
• University of Lleida（莱里达大学）

机构由 AI 辅助整理，请以论文原文为准。