Human–robot collaboration in building disassembly: a multi-agent LLM architecture
Building disassembly is critical for circular economy material reuse, yet remains rare due to cost and safety constraints, leading to demolition and material downcycling. Automation could improve both efficiency and safety, but currently available technology does not yet enable full automation. We propose a human–robot collaboration system architecture that uses agentic large language models. We test this approach in building disassembly—an unstructured, safety–critical domain where conventional pre-programmed robotics are inadequate. The agentic architecture combines curated domain knowledge, physics simulation for stability validation, and natural language interfaces, enabling the robot to participate through proactive reasoning rather than follow control commands. We evaluated the architecture through three progressively complex scenarios: collaborative spatial adaptation, collaborative decision-making, and learning. The main contribution is a modular, data-grounded HRC methodology in which specialized LLM agents perform agentic reasoning: the robot assesses situations, retrieves relevant procedural knowledge, validates decisions through simulation, and negotiates solutions with human operators. This proof of concept demonstrates that agentic multi-agent LLM systems can enable adaptive human–robot collaboration under uncertainty, beyond natural language interfaces through integrated domain knowledge, physics validation, and agentic reasoning.