HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments
This addresses safety for workers in hazardous DOE sites, but it appears incremental as it builds on existing AI and human collaboration methods.
The paper tackles proactive hazard forecasting in high-risk Department of Energy environments by developing HARNESS, a modular AI framework that integrates LLMs with structured data and human-in-the-loop refinement, showing promising preliminary results.
Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework designed to forecast hazardous events and analyze operational risks in U.S. Department of Energy (DOE) environments. HARNESS integrates Large Language Models (LLMs) with structured work data, historical event retrieval, and risk analysis to proactively identify potential hazards. A human-in-the-loop mechanism allows subject matter experts (SMEs) to refine predictions, creating an adaptive learning loop that enhances performance over time. By combining SME collaboration with iterative agentic reasoning, HARNESS improves the reliability and efficiency of predictive safety systems. Preliminary deployment shows promising results, with future work focusing on quantitative evaluation of accuracy, SME agreement, and decision latency reduction.