用大模型自动优化厂房建造计划，减少人工干预。
CONSTRUCTA: Automating Commercial Construction Schedules in Fabrication Facilities with Large Language Models
- 结合建筑知识库与上下文采样，提升输入质量。
- 在缺失值预测上提升42.3%，依赖分析提升79.1%。
- 适合建筑、制造领域自动化调度研究者参考。
将大语言模型应用于自动化规划，为传统行业带来变革机遇，但实际应用仍不充分。在商业建造领域，复杂项目常需人工干预以确保精度。本文提出CONSTRUCTA框架，利用大模型优化半导体厂房等复杂项目的施工进度安排。该框架通过三项创新：(1) 静态RAG集成建筑领域知识；(2) 借鉴建筑设计经验的上下文采样技术；(3) 采用建筑领域DPO，基于强化学习人类反馈（RLHF）对齐专家偏好。在私有数据集上的实验显示，相比基线方法，其在缺失值预测上提升42.3%，依赖关系分析提升79.1%，自动化排程能力提升28.9%，展现出革新建造流程的巨大潜力，并推动领域专用大模型的发展。
原文摘要 · Abstract (English)
Automating planning with LLMs presents transformative opportunities for traditional industries, yet remains underexplored. In commercial construction, the complexity of automated scheduling often requires manual intervention to ensure precision. We propose CONSTRUCTA, a novel framework leveraging LLMs to optimize construction schedules in complex projects like semiconductor fabrication. CONSTRUCTA addresses key challenges by: (1) integrating construction-specific knowledge through static RAG; (2) employing context-sampling techniques inspired by architectural expertise to provide relevant input; and (3) deploying Construction DPO to align schedules with expert preferences using RLHF. Experiments on proprietary data demonstrate performance improvements of +42.3% in missing value prediction, +79.1% in dependency analysis, and +28.9% in automated planning compared to baseline methods, showcasing its potential to revolutionize construction workflows and inspire domain-specific LLM advancements.
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。