Developing an AI Assistant for Knowledge Management and Workforce Training in State DOTs

Researchers propose a Retrieval-Augmented Generation (RAG) framework with multi-agent architecture to improve knowledge management and workforce training in state transportation departments. The system combines specialized AI agents for document retrieval, answer generation, and quality control, including vision-language models to process technical figures alongside text.

• →Traditional knowledge management in state DOTs suffers from fragmented transfer and expertise loss as senior engineers retire.
• →The proposed RAG framework uses multiple specialized AI agents rather than conventional single-pass systems for better quality control.
• →The system integrates vision-language models to convert technical figures into searchable text representations.
• →The framework aims to help engineers quickly locate relevant information from vast technical documentation.
• →Multi-agent architecture enables iterative improvement and real-time, context-aware response generation.