用大语言模型智能体改进约束模型
Improving Constraint Models with LLM Agents
- TU Wien（维也纳技术大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出一种基于LLM智能体的框架，通过迭代诊断修复改进约束模型，在9个组合优化问题的27个测试实例中多数表现优于原模型，部分问题求解速度提升超两个数量级，证明自主智能体方法可支持约束模型优化。
AI中文摘要：
约束规划（CP）求解器的运行时间对建模选择高度敏感，这些选择包括对称性破缺、隐含约束、全局约束、约束重构和变量表示。改进这些约束模型传统上需要人类专业知识，而现有的自动重构系统仅限于预定义的手工转换规则库。我们引入一种智能体框架，该框架从开放空间重构约束模型，并通过经验而非构造建立正确性：给定一个模型和三个训练实例，大语言模型（LLM）智能体会提出替代公式，通过将其解注入原始模型来验证每个公式，并诊断和修复失败，在大约15分钟的中位数时间内返回找到的最佳变体。这些模型用CPMpy建模库表示，每个提出的模型在三个更大的测试实例上进行评估。在九个组合优化问题中，生成的模型在27个测试实例中的21个上优于原始模型，在一些问题上求解速度快两个数量级以上。与使用相同验证和选择工具的非智能体基线的比较表明，这些改进源于智能体的迭代诊断和修复，而不仅仅是对多个候选的采样。这些结果表明，自主智能体方法可以支持约束模型的改进。
英文摘要：
The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as symmetry breaking, implied constraints, global constraints, constraint reformulation, and variable representation. Improving these constraint models has traditionally required human expertise, and existing automated reformulation systems are restricted to a predefined library of hand-crafted transformation rules. We introduce an agentic framework that instead reformulates a constraint model from an open-ended space and establishes correctness empirically rather than by construction: a Large Language Model (LLM) agent, given a model and three training instances, proposes alternative formulations, validates each by injecting its solution back into the original model, and diagnoses and repairs failures, returning the best variant it finds in a median of about fifteen minutes. The models are expressed in the CPMpy modeling library, and each proposed model is evaluated on three larger test instances. Across nine combinatorial optimization problems, the generated models outperform the originals on 21 of 27 test instances, and on some problems solve more than two orders of magnitude faster. A comparison against non-agentic baselines that reuse the same validation and selection tools indicates that the gains stem from the agent's iterative diagnosis and repair, not merely from sampling several candidates. These results demonstrate that autonomous agentic methods can support the improvement of constraint models.
