Supporting Construction Worker Well-Being with a Multi-Agent Conversational AI System

TL;DR

This paper presents a multi-agent conversational AI system tailored for construction workers that enhances their well-being by providing practical support and social interaction, demonstrating significant improvements over single-agent systems.

Contribution

The paper introduces a novel multi-agent AI system with domain-specific knowledge and distinct personas to support construction workers' mental health and practical needs.

Findings

System outperforms single-agent baseline in usability by 18%

Increases in self-determination by 40%

Enhances social presence and trust by 60%

Abstract

The construction industry is characterized by both high physical and psychological risks, yet supports of mental health remain limited. While advancements in artificial intelligence (AI), particularly large language models (LLMs), offer promising solutions, their potential in construction remains largely underexplored. To bridge this gap, we developed a conversational multi-agent system that addresses industry-specific challenges through an AI-driven approach integrated with domain knowledge. In parallel, it fulfills construction workers' basic psychological needs by enabling interactions with multiple agents, each has a distinct persona. This approach ensures that workers receive both practical problem-solving support and social engagement, ultimately contributing to their overall well-being. We evaluate its usability and effectiveness through a within-subjects user study with 12 participants. The results show that our system significantly outperforms the single-agent baseline, achieving improvements of 18% in usability, 40% in self-determination, 60% in social presence, and 60% in trust. These findings highlight the promise of LLM-driven AI systems in providing domain-specific support for construction workers.