ABSTRACT The growing complexity of construction management (CM) projects, coupled with challenges such as strict regulatory requirements and labor shortages, requires specialized analytical tools that streamline project workflow and enhance performance. Although large language models (LLMs) have demonstrated exceptional performance in general reasoning tasks, their effectiveness in tackling CM-specific challenges, such as precise quantitative analysis and regulatory interpretation, remains inadequately explored. To bridge this gap, this study introduces CMExamSet, a comprehensive benchmarking dataset comprising 689 authentic multiple-choice questions sourced from 1 arXiv:2504.08779v1 The results indicate that GPT-4o and Claude 3.7 surpass typical human pass thresholds (70%), with average accuracies of 82% and 83%, respectively. Additionally, both models performed better on single-step tasks, with accuracies of 85.7% (GPT-4o) and 86.7% (Claude 3.7). Multi-step tasks were more challenging, reducing performance to 76.5% and 77.6%, respectively. Our error pattern analysis further reveals that conceptual misunderstandings are the most common (44.4% and 47.9%), underscoring the need for enhanced domain-specific reasoning models. These findings underscore the potential of LLMs as valuable supplementary analytical tools in CM, while highlighting the need for domain-specific refinements and sustained human oversight in complex decision making. INTRODUCTION The construction industry is undergoing a transformation driven by digital technologies, increased project complexity, heterogeneous regulations, and ongoing labor shortages (Abioye et al. 2021). These changes create a pressing need for intelligent tools that can augment human expertise and support decision-making in construction management (CM) (Regona et al. 2022). Among these technologies, large language models (LLMs) such as GPT-4 and Claude have shown a comparative performance in general reasoning, natural language understanding, and educational applications (Ooi et al. 2025).

The construction industry faces numerous hurdles that have hampered its expansion and resulted in exceptionally low productivity levels. Artificial intelligence and its applications have completely altered the landscape of the construction industry. The construction industry is one of the least digital in the world, with most players acknowledging a long-standing culture of resistance to change. The lack of digitization and the industry's extremely manual character make project management more complex and time-consuming than it needs to be. When compared to traditional procedures, AI techniques have helped to improve automated processes and create superior competitive advantages.

Whether you use artificial or augmented with intelligence, AI (artificial intelligence) is catching on in the industry. Recent announcements include its use in field and office alike. For example, Black & Veatch is implementing Zinier's intelligent field service automation platform, ISAC, (Intelligent Service Automation and Control) to deepen realtime visibility into the field, to anticipate service disruptions through AI-driven recommendations, and to improve operational efficiencies by automating manual front-office, backoffice, and field-office tasks. ISAC will help ensure faster, more seamless communication among Black & Veatch's extensive field services workforce. According to Zinier, ISAC is the eyes, ears, and algorithms that analyze an organization's past and present.

Site-Layout Modeling: How AI Can Help Construction Industry? The efficient planning of site space through the construction project is referred to as site layout planning. Due to its impact on safety, productivity and security on construction sites, several site layout planning models have been developed in the past decades. These models have the common aim of generating best layouts considering the defined constraints and conditions. However, the underlying assumptions that were made during the development of these models seem disparate and often implicit.