用推理大模型自动解运筹优化问题，三阶段分工更准确。
OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
- 分建模、编码、调试三阶段，每个环节由专用子代理处理。
- 在自建数据集BWOR上，准确率比GPT-o3等领先7%以上。
- 适合想自动化求解复杂优化问题的研究者和工程师。
随着人工智能的发展，将大语言模型（LLM）应用于数学问题求解受到越来越多关注。现有方法多通过提示工程或微调提升运筹学（OR）优化问题的求解能力，但受限于非推理型LLM的能力。为此，本文提出OR-LLM-Agent框架，基于推理型大模型实现运筹优化问题的自动化求解。该框架将任务分解为数学建模、代码生成和调试三个阶段，每个阶段由专门子代理负责，实现更精准的推理。同时构建了用于评估LLM在运筹学任务中表现的BWOR数据集。分析显示，在NL4OPT、MAMO和IndustryOR基准测试中，某些推理型模型甚至不如同系列非推理模型；而BWOR能提供更一致且区分度更高的评估。实验表明，采用DeepSeek-R1的OR-LLM-Agent在准确率上优于GPT-o3、Gemini 2.5 Pro、DeepSeek-R1及ORLM等先进方法至少7%。结果验证了任务分解在运筹优化求解中的有效性。
原文摘要 · Abstract (English)
With the rise of artificial intelligence (AI), applying large language models (LLMs) to mathematical problem-solving has attracted increasing attention. Most existing approaches attempt to improve Operations Research (OR) optimization problem-solving through prompt engineering or fine-tuning strategies for LLMs. However, these methods are fundamentally constrained by the limited capabilities of non-reasoning LLMs. To overcome these limitations, we propose OR-LLM-Agent, an AI agent framework built on reasoning LLMs for automated OR problem solving. The framework decomposes the task into three sequential stages: mathematical modeling, code generation, and debugging. Each task is handled by a dedicated sub-agent, which enables more targeted reasoning. We also construct BWOR, an OR dataset for evaluating LLM performance on OR tasks. Our analysis shows that in the benchmarks NL4OPT, MAMO, and IndustryOR, reasoning LLMs sometimes underperform their non-reasoning counterparts within the same model family. In contrast, BWOR provides a more consistent and discriminative assessment of model capabilities. Experimental results demonstrate that OR-LLM-Agent utilizing DeepSeek-R1 in its framework outperforms advanced methods, including GPT-o3, Gemini 2.5 Pro, DeepSeek-R1, and ORLM, by at least 7\% in accuracy. These results demonstrate the effectiveness of task decomposition for OR problem solving.
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。