Scalability Constraints in AI-Driven Construction Management: Opportunities for Robotics and LLM Integration
TL;DR
The findings indicate that scalability should be understood not merely as increasing computational capacity but as the ability to expand AI-enabled construction processes without proportionally increasing coordination complexity, training requirements, or operational risk.
Abstract
The increasing digitization of construction management has created opportunities for artificial intelligence (AI), robotics, cloud architectures, and large language models (LLMs) to support planning, coordination, monitoring, and operational decision-making. However, scalability remains a fundamental challenge because construction environments are characterized by heterogeneous workflows, distributed information, changing operational conditions, and uneven levels of technological adoption. This research and review paper examines the principal scalability constraints affecting AI-driven construction management and investigates how robotics and LLM integration can address selected operational and informational limitations. The study adopts a conceptual qualitative methodology based on grounded-theory principles, systematic interpretation of the provided literature, and cross-domain synthesis. The analysis identifies four interconnected scalability dimensions: technological infrastructure, organizational routines, human-system interaction, and learning and decision-support capacity. Cloud-oriented architectures provide a foundation for distributed computational access, while research on learning systems indicates that sustained technology adoption depends on perceived usefulness, quality, task value, and user capability. Grounded-theory studies further indicate that organizational routines and methodological processes influence how emerging technologies become embedded in operational practice. Within this framework, robotics can extend AI from informational decision support toward physical execution, whereas LLMs can improve the accessibility, interpretation, and coordination of heterogeneous construction information. The paper proposes an integrated scalability framework in which infrastructure, organizational routines, human learning, LLM-based intelligence, and robotic execution are treated as mutually dependent components rather than isolated technologies. The findings indicate that scalability should be understood not merely as increasing computational capacity but as the ability to expand AI-enabled construction processes without proportionally increasing coordination complexity, training requirements, or operational risk.