让大模型学会选优化建模策略，提升代码正确率和求解效率。
Strategy-Aware Optimization Modeling with Reasoning LLMs
- 显式建模策略，通过验证数据与多策略训练提升可靠性。
- 在8个基准上平均通过率从72.7提升至80.3，约束数减少14.2%。
- 适合自动化建模、求解器优化及工业级应用开发者使用。
大型语言模型能生成语法正确的优化程序，但常无法可靠选择有效建模策略，导致公式错误和求解器效率低下。我们提出SAGE框架，将建模策略显式融入数据构建与后训练过程。SAGE构建了一个经求解器验证的多策略数据集，并采用监督微调结合分段加权GRPO的方法，以格式合规性、正确性和求解效率为复合奖励进行训练。在涵盖合成与真实场景的八个基准上，SAGE将平均pass@1的通过率从72.7提升至80.3，超过最强开源基线。多次生成下，SAGE发现更多不同且正确的建模形式，pass@16时组件级多样性提升19-29%。在最大规模下，其生成的约束系统比基线少14.2%的约束，符合高效求解需求。结果表明，显式建模策略能显著提升自动优化建模效果。代码已公开于https://github.com/rachhhhing/SAGE。
原文摘要 · Abstract (English)
Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a strategy-aware framework that makes Modeling Strategy explicit in both data construction and post-training. SAGE builds a solver-verified multi-strategy dataset and trains a student model with supervised fine-tuning followed by Segment-Weighted GRPO using a composite reward over format compliance, correctness, and solver efficiency. Across eight benchmarks spanning synthetic and real-world settings, SAGE improves average pass@1 from 72.7 to 80.3 over the strongest open-source baseline. With multiple generations, SAGE discovers more distinct correct formulations and improves component-level diversity at pass@16 by 19-29%. At the largest scale, SAGE produces more compact constraint systems with 14.2% fewer constraints than the baseline, consistent with solver-efficient modeling. Overall, these results show that making Modeling Strategy explicit improves automated optimization modeling. Code is available at https://github.com/rachhhhing/SAGE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。