用大模型解决不确定条件下的自动优化问题，提升决策鲁棒性。
DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs
- 构建多智能体框架，结合领域知识增强大模型建模能力
- 提出新数据集OptU，支持在不确定场景下评估模型可行性
- 聚焦实际应用中的鲁棒性与泛化能力，适合工业优化研究者
大语言模型的进展推动了自动化优化建模的发展。然而，现实决策普遍存在不确定性，而现有工作大多聚焦于参数已知的确定性优化，未充分探索大模型在不确定环境中的应用。为此，我们提出DAOpt框架，包含新数据集OptU、多智能体决策模块以及用于评估大模型的仿真环境，重点考察其在样本外的可行性与鲁棒性。此外，通过引入随机优化与鲁棒优化的少量示例知识，增强大模型的建模能力。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) have accelerated research on automated optimization modeling. While real-world decision-making is inherently uncertain, most existing work has focused on deterministic optimization with known parameters, leaving the application of LLMs in uncertain settings largely unexplored. To that end, we propose the DAOpt framework including a new dataset OptU, a multi-agent decision-making module, and a simulation environment for evaluating LLMs with a focus on out-of-sample feasibility and robustness. Additionally, we enhance LLMs' modeling capabilities by incorporating few-shot learning with domain knowledge from stochastic and robust optimization.
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。