2026/04/02 by Zhijing Hu, Yufan Deng, Haoyang Liu +1 · 1 voice
Computer Science · Materials Science · #Benchmark (surveying) #Bridge (graph theory) #Bridging (networking) #Constraint Satisfaction and Optimization #Executable #Machine Learning and Data Classification #Machine Learning in Materials Science #Modeling language #Nonlinear system #Semantic mapping #Semantics (computer science) #Solver #cs.AI
paper · pdf · open access · doi:10.48550/arxiv.2604.01588
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2026/04/02 · arxiv published 2026/04/02 · arxiv updated 2026/04/02 · openalex created_date 2026/04/04 · openalex updated_date 2026/07/28
Automating the translation of Operations Research (OR) problems from natural language to executable models is a critical challenge. While Large Language Models (LLMs) have shown promise in linear tasks, they suffer from severe performance degradation in real-world nonlinear scenarios due to semantic misalignment between mathematical formulations and solver codes, as well as unstable information extraction. In this study, we introduce NED-Tree, a systematic framework designed to bridge the semantic gap. NED-Tree employs (a) a sentence-by-sentence extraction strategy to ensure robust parameter mapping and traceability; and (b) a recursive tree-based structure that adaptively decomposes complex nonlinear terms into solver-compatible sub-elements. Additionally, we present NEXTOR, a novel benchmark specifically designed for complex nonlinear, extensive-constraint OR problems. Experiments across 10 benchmarks demonstrate that NED-Tree establishes a new state-of-the-art with 72.51% average accuracy, NED-Tree is the first framework that drives LLMs to resolve nonlinear modeling difficulties through element decomposition, achieving alignment between modeling semantics and code semantics. The NED-Tree framework and benchmark are accessible in the anonymous repository https://anonymous.4open.science/r/NORA-NEXTOR.