发表机构
Gurobi; IBM（古罗比; 国际商业机器公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究自然语言到优化建模问题，核心方法是基于简化验证理念，利用优化求解器生成诊断查询让大语言模型推理公式正确性，主要贡献是在优化基准测试中提升准确性并提供高精度自验证信号。
AI 中文摘要
自然语言接口可极大提升优化建模的可及性与可用性，大语言模型在将文本问题描述自动转换为可执行求解器公式方面展现出潜力。然而，现有方法的关键挑战在于确保推断的公式能正确实现预期任务。我们引入了VeriSimpl，一个用于鲁棒自然语言到优化形式化的求解器大语言模型框架。我们的方法基于简化验证理念，利用优化求解器生成关于候选公式的简化诊断查询，使大语言模型能在固定全局上下文中局部推理公式的正确性。我们展示了针对问题约束和决策变量在不同维度的简化策略。在一系列优化基准测试中的评估表明，我们的方法在准确性上比现有方法有持续提升，还提供了一种新型高精度自验证信号。
英文摘要
Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (LLMs) show promise in automatically translating textual problem descriptions into executable solver formulations. However, a key challenge for existing approaches is to ensure that the inferred formulation correctly implements the intended task, even if it may execute without errors. We introduce VeriSimpl, a solver LLM framework for robust natural-language-to-optimization formalization. Our approach is based on the idea of simplification-based verification, where the optimization solver is leveraged to generate simplified diagnostic queries about a candidate formulation to allow the LLM to tractably reason about the correctness of the formulation with respect to the task description. We present such simplification strategies along different dimensions with respect to problem constraints and decision variables, which allow the LLM to reason locally under fixed global contexts. Evaluations on a range of optimization benchmarks show how our approach provides consistent improvements in accuracy over existing methods, while also providing a novel high-precision self-verification signal.
CommentsAccepted and published at ICML 2026. Code available at https://github.com/suabar/VeriSimple
