arXiv：cs.AI· Rafa{\l} Stachowiak, Tomasz P. Pawlak·· 13 小时前
MPMMine：面向约束获取的更优基准套件
MPMMine: Better Benchmarks for Constraint Acquisition
AI 导读
MPMMine 是一个用于评估约束获取（CA）算法的基准套件，旨在解决现有基准组织松散、格式不一致、面向求解器而非 CA 算法等问题。它按统一结构和开放格式，为每个问题提供多种 MP 模型公式、每个模型数十个参数实例化，以及离散、连续和混合域中数千个示例解与非解，并附自然语言描述以支持 text-to-model 方法。
正文
Abstract:Constraint Acquisition (CA) and related research on the validation and enhancement of Mathematical Programming (MP) models using domain knowledge artifacts are currently limited by inadequate benchmarks. The existing benchmarks are loosely organized, provide inconsistent types and formats of artifacts for individual problems, are designed for benchmarking solvers rather than CA algorithms, include narrow classes of problems, or omit crucial details for the reproducibility of experiments and fair comparison of CA methods.
We develop a benchmark dataset, a supporting software package, and a benchmarking tool crafted for the consistent, systematic, and comprehensive assessment of CA algorithms, bridging the gap in algorithmic development and experimental infrastructure.
This work presents MPMMine, a benchmark suite designed to assess algorithms that discover, validate, and enhance MP models using diverse artifacts. The development of MPMMine is guided by design rules supporting consistency, standardization, completeness, extensibility, openness, and version control. It adopts a uniform structure and relies on open formats. It provides alternative formulations of MP models per problem, tens of parameter instantiations per MP model, and thousands of exemplary solutions and non-solutions in discrete, continuous, and mixed domains, alongside natural-language descriptions to support text-to-model methods. The mpmmine-py Python package provides an application programming interface for accessing the dataset artifacts. The MPMMine Leaderboard is a~tool that systematically evaluates existing CA algorithms using MPMMine under consistent conditions. It leverages open source implementations, runs them in isolated containers adapting input/output to their needs to build an extensive, interactive scoreboard.
| Comments: | 19 pages, 1 figure, for the associated dataset, see this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) |
| MSC classes: | 90C90 (Primary), 90C05 (Secondary) |
| ACM classes: | I.6.3; I.2.2; I.2.7 |
| Cite as: | arXiv:2605.26279 [cs.AI] |
| (or arXiv:2605.26279v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.26279 arXiv-issued DOI via DataCite |
Submission history
From: Tomasz Pawlak [view email]
[v1]
Mon, 25 May 2026 19:05:12 UTC (801 KB)
[v2]
Fri, 9 Oct 2026 16:22:45 UTC (810 KB)
来源：arXiv：cs.AI · arxiv.org