arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09635cs.AIcs.LG
收藏

大规模优化模型自动生成:通过结构化工作流利用LLM的灵活性

Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow

Shanghai Jiao Tong University(上海交通大学);National University of Singapore(新加坡国立大学);Imperial Business School(帝国理工商学院);City University of Hong Kong(香港城市大学);Purdue University(普渡大学);Cornell University(康奈尔大学)

Kuo Liang, Yuhang Lu, Jianming Mao, Shuyi Sun, Chunwei Yang, Congcong Zeng, Xiao Jin, Hanzhang Qin, Ruihao Zhu, Chung-Piaw Teo

AI总结:

LEAN-LLM-OPT通过结构化工作流利用LLM灵活性,实现大规模优化模型自动生成,并在多个场景中展现优越性能。

摘要:

大规模优化是现代商业决策的关键支柱。然而,构建这些模型往往耗费大量人力和时间。我们通过提出LEAN-LLM-OPT,一种轻量级的结构化工作流构建框架,来解决这一问题。LEAN-LLM-OPT接受问题描述及其相关数据集,并协调一组LLM代理生成优化模型。具体而言,当接收到查询时,两个上游LLM代理动态构建一个工作流,逐步指定如何为类似问题生成优化模型。下游LLM代理则根据此工作流生成最终输出。这种代理工作流利用常见的建模实践,将建模过程结构化为一系列子任务,将机械的数据处理操作委托给辅助工具。这减少了LLM在规划和数据处理方面的负担,使我们能够利用其灵活性来处理非结构化组件。广泛的模拟显示,使用GPT-4.1和开源gpt-oss-20B实例化的LEAN-LLM-OPT在大规模优化建模任务中表现出色,并与最先进的方法相竞争。此外,在新加坡航空的选择性收入管理用例中,LEAN-LLM-OPT展示了实际价值,通过在多种场景中取得领先表现。在此过程中,我们引入了大规模OR和Air-NRM,这是大规模优化自动生成的第一个综合性基准。该工作的代码和数据可在https://github.com/CoraLiang01/lean-llm-opt上获得。

英文摘要:

Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We address this by proposing LEAN-LLM-OPT, a LightwEight AgeNtic workflow construction framework for LLM-assisted large-scale OPTimization auto-formulation. LEAN-LLM-OPT takes as input a problem description together with associated datasets and orchestrates a team of LLM agents to produce an optimization formulation. Specifically, upon receiving a query, two upstream LLM agents dynamically construct a workflow that specifies, step-by-step, how optimization models for similar problems can be formulated. A downstream LLM agent then follows this workflow to generate the final output. The agentic workflow leverages common modeling practices to structure the modeling process into a sequence of sub-tasks, offloading mechanical data-handling operations to auxiliary tools. This reduces the LLM's burden in planning and data handling, allowing us to exploit its flexibility to address unstructured components. Extensive simulations show that LEAN-LLM-OPT, instantiated with GPT-4.1 and the open source gpt-oss-20B, achieves strong performance on large-scale optimization modeling tasks and is competitive with state-of-the-art approaches. In addition, in a Singapore Airlines choice-based revenue management use case, LEAN-LLM-OPT demonstrates practical value by achieving leading performance across a range of scenarios. Along the way, we introduce Large-Scale-OR and Air-NRM, the first comprehensive benchmarks for large-scale optimization auto-formulation. The code and data of this work is available at https://github.com/CoraLiang01/lean-llm-opt.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑