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

2025-11-13

AI Summary

To address the delayed passive response to hazardous incidents and insufficient interpretability of risk analysis in high-risk operational environments at the U.S. Department of Energy, this paper proposes a modular AI framework that integrates large language models with structured work order data. The framework enables historical incident retrieval, human-AI collaborative decision-making, and expert-feedback-driven iterative agent reasoning. Its key contribution lies in the novel incorporation of expert-in-the-loop mechanisms, establishing an adaptive learning closed loop that significantly enhances prediction accuracy and decision transparency. Preliminary deployment demonstrates superior reliability in risk early warning and improved responsiveness. Subsequent work will quantitatively evaluate the framework’s gains in predictive precision, expert consensus alignment, and reduction in decision latency.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Reasoning under Uncertainty: Sequential Decision Making
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Forecasting hazardous events in high-risk DOE operational environments
• Analyzing operational risks through AI and historical data integration
• Enhancing predictive safety via human-agent collaboration and adaptive learning

Innovation

• Modular AI framework integrating LLMs with structured data
• Human-in-the-loop mechanism allowing expert prediction refinement
• Combines SME collaboration with iterative agentic reasoning