Automated data to model transformation for constraint programming with AI

Artificial intelligence for combinatorial optimization depends on high-quality, structured training data, yet transforming ambiguous natural-language descriptions into precise, executable formal models remains a major bottleneck, traditionally requiring extensive manual effort and domain expertise. We develop CPAM-LLM, an automated constraint-programming modeling framework based on large language models that converts unstructured problem specifications into validated and executable formal models. The framework integrates retrieval-augmented generation grounded in formal concept analysis for structural validation, chaos-mapping-based data augmentation to enhance cross-domain generalization, and dynamic constraint adaptation to accommodate evolving problem settings. We demonstrate its effectiveness across five scenarios, including DNA sequence design, reconfigurable energy storage systems, and unmanned vehicle logistics. The results show that the framework can automate the data-to-model pipeline while adapting reliably to changing requirements, providing a practical approach to automated data formalization and indicating the importance of accessible, high-quality structured data for reliable downstream artificial intelligence applications.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-11-19
DOI
https://doi.org/10.1038/s41467-026-78715-2
Primary Topic
Constraint Satisfaction and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Automated data to model transformation for constraint programming with AI

Zhengqi Shi, Liang Gao, Qihao Liu, Xinyu Li et al.
Nature Communications
Constraint Satisfaction and Optimization
article

Automated data to model transformation for constraint programming with AI

Zhengqi Shi, Liang Gao, Qihao Liu, Xinyu Li, Mingming Peng, Jin Huang, Chunjiang Zhang, Shaosen Su, Peigen Li, Hao Zhang, Xinyi Yang
article en

Abstract

Artificial intelligence for combinatorial optimization depends on high-quality, structured training data, yet transforming ambiguous natural-language descriptions into precise, executable formal models remains a major bottleneck, traditionally requiring extensive manual effort and domain expertise. We develop CPAM-LLM, an automated constraint-programming modeling framework based on large language models that converts unstructured problem specifications into validated and executable formal models. The framework integrates retrieval-augmented generation grounded in formal concept analysis for structural validation, chaos-mapping-based data augmentation to enhance cross-domain generalization, and dynamic constraint adaptation to accommodate evolving problem settings. We demonstrate its effectiveness across five scenarios, including DNA sequence design, reconfigurable energy storage systems, and unmanned vehicle logistics. The results show that the framework can automate the data-to-model pipeline while adapting reliably to changing requirements, providing a practical approach to automated data formalization and indicating the importance of accessible, high-quality structured data for reliable downstream artificial intelligence applications.

Nature Communications
Huazhong University of Science and Technology (CN)
Constraint Satisfaction and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon