Residential construction projects are characterized by high complexity, fragmented communication, and vulnerability to delays and budget overruns due to inefficient manual coordination. This paper presents Civil2PM, an adaptive, on-premises multi-agent project lifecycle management (PLM) system built to autonomously oversee the entire life cycle of residential construction projects. The system is designed to ensure robust cyber-security, maintain cost-efficiency, and seamlessly integrate with existing building information modeling (BIM) and enterprise resource planning (ERP) infrastructure. It employs compact yet high-performance large language models (LLMs), Phi-4-14B, and Qwen3-30B-A3B, running locally to ensure both speed and data sovereignty. These models are orchestrated through the LangChain framework, enhanced with agentic retrieval-augmented generation (ARAG), and supported by a dual-protocol architecture comprising the agent-to-agent (A2A) and model context protocol (MCP). The A2A protocol enables secure, structured communication among specialized artificial intelligence (AI) agents (initiation, tracking, and reporting), while MCP provides standardized and isolated access to enterprise data sources. Civil2PM was trained and contextualized on 3500 real-world residential construction project cards, enabling it to autonomously generate project plans, track progress, issue communications, and update databases. By automating these processes, the system significantly reduces human errors in project coordination. A multi-phase evaluation with 11 medium and large construction enterprises demonstrated the system’s capability to reduce coordination latency, improve schedule adherence, and eliminate dependence on costly cloud application programming interface (APIs). This work contributes a novel agentic-AI-driven architecture for residential construction sector, merging compact LLMs, multi-agent coordination, and secure local deployment to address pressing economic and operational challenges.

Disjointed coordination between design, management, engineering, and production teams continues to hamper efficiency in various residential construction projects. This disconnection leads to costly delays in material specification approval, production scheduling, and component shipment. To address this issue, a multi-agent system (MAS) is developed to automate enterprise resource planning (ERP) workflows for the procurement, ordering, manufacturing, and shipping of reinforced concrete structural elements in residential housing construction. By leveraging the cohesive power of the compact large language model (Phi-4-14B) and the model context protocol (MCP), the system enhances communication between artificial intelligence (AI) agents and human stakeholders, ensuring robust coordination across design validation, structural analysis, and manufacturing logistics. The data parser agent digitizes and verifies material specifications, whereas the structural analyst agent employs an accelerated stochastic finite element analysis (SFEA), utilizing Subset Simulation and physics-informed neural network (PINN) for rapid convergence without compromising accuracy. The workflow communicator agent ensures closed-loop ERP integration, synchronizing project approvals, and dispatching validated designs for production, with Internet of Things (IoT)-based tracking providing real-time status updates. By generating interpretable portable document format/comma-separated values (PDF/CSV) reports detailing stress–strain curves, probabilistic failure modes, and sensitivity analyses, the system minimizes manual intervention while maintaining engineer oversight. Case studies conducted across 20 residential construction companies demonstrate an 88% reduction in coordination errors and a 71% improvement in lead time, particularly for high-variability concrete materials. This study establishes a novel AI-driven framework that bridges MAS and ERP systems, offering a scalable, autonomous enterprise digital management solution to streamline the lifecycle of reinforced concrete structural elements from specification approval to on-site delivery.