arXiv cs.AI· Rui Zhang, Chenyu Zhou, Jianghao Lin, Yaoxin Wu, Dongdong Ge, Wen Song·· 13 小时前AI 评分31
ORSMT：用可满足性模理论为 LLM 优化建模提供语义验证与修复
ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization
AI 导读
ORSMT 通过类型化语义接口和精确 SMT 关系查询，对 LLM 生成的优化模型、求解器代码与报告做语义比对，可证明或反驳可行域与目标关系并定位到具体行或域。
正文 · 原文
Abstract:Large language models increasingly automate optimization modeling from natural language problems, producing written mathematics, solver code and a returned report. Verifying one optimization problem across these artifacts requires semantic comparison: unequal models can attain the same objective, equivalent models can use different auxiliary variables, and mutually consistent artifacts can omit the same source requirement. ORSMT provides a typed semantic interface and exact SMT relation queries. It aligns observable decisions, projects auxiliary variables, proves or refutes feasible region and objective relations, localizes refutations to implicated rows or domains and links source texts when available. It then reconstructs one artifact from another, and each adopted candidate passes the required relation checks. Across 3,034 problems and six generator sizes, ORSMT improves the model-code match rate in all 72 benchmark and generator combinations before selection. Protected selection raises the aggregate rate from 43.2% to 88.2% and the share that are both correct and matched from 25.2% to 40.2%. On the 1,905 refuted outputs, certified voting under the shared fallback makes 50.9% of outputs correct and matched, compared with 44.8% for ReLoop and 49.4% for Opt-Verifier. A separate one-round source revision followed by exact reconstruction restores a model-code match for 84.4% of the refuted pairs.
| Subjects: | Optimization and Control (math.OC); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.29145 [math.OC] |
| (or arXiv:2610.29145v1 [math.OC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29145 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rui Zhang [view email]
[v1]
Wed, 21 Oct 2026 03:27:02 UTC (3,062 KB)
来源：arXiv cs.AI · arxiv.org