HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments

2025/11/13 by Ran Elgedawy, Sanjay Das, Elgedawy, Ran +16
Health Professions · Engineering · Decision Sciences · #Occupational Health and Safety Research #Maritime Navigation and Safety #Risk and Safety Analysis

paper · pdf · doi:10.48550/arxiv.2511.10810

Abstract

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.

Related

• A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management
• A Comprehensive Review of Human Error in Risk-Informed Decision Making: Integrating Human Reliability Assessment, Artificial Intelligence, and Human Performance Models
• Adapting Probabilistic Risk Assessment for AI
• Unsafe at any AUC: Unlearned Lessons From Sociotechnical Disasters for Responsible AI
• Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resilience