DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911266326446080 |
|---|---|
| author | Zhu, WenZhuo Cui, Zheng Lu, Wenhan Liu, Sheng Zhao, Yue |
| author_facet | Zhu, WenZhuo Cui, Zheng Lu, Wenhan Liu, Sheng Zhao, Yue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11576 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs Zhu, WenZhuo Cui, Zheng Lu, Wenhan Liu, Sheng Zhao, Yue Machine Learning Artificial Intelligence 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. |
| title | DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11576 |