Saved in:
Bibliographic Details
Main Authors: Elgedawy, Ran, Das, Sanjay, Seefried, Ethan, Wiggins, Gavin, Burchfield, Ryan, Hewit, Dana, Srinivasan, Sudarshan, Thomas, Todd, Balaprakash, Prasanna, Ghosal, Tirthankar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10810
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908651193630720
author Elgedawy, Ran
Das, Sanjay
Seefried, Ethan
Wiggins, Gavin
Burchfield, Ryan
Hewit, Dana
Srinivasan, Sudarshan
Thomas, Todd
Balaprakash, Prasanna
Ghosal, Tirthankar
author_facet Elgedawy, Ran
Das, Sanjay
Seefried, Ethan
Wiggins, Gavin
Burchfield, Ryan
Hewit, Dana
Srinivasan, Sudarshan
Thomas, Todd
Balaprakash, Prasanna
Ghosal, Tirthankar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments
Elgedawy, Ran
Das, Sanjay
Seefried, Ethan
Wiggins, Gavin
Burchfield, Ryan
Hewit, Dana
Srinivasan, Sudarshan
Thomas, Todd
Balaprakash, Prasanna
Ghosal, Tirthankar
Artificial Intelligence
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.
title HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments
topic Artificial Intelligence
url https://arxiv.org/abs/2511.10810