NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Rooms

TL;DR

NuHF Claw introduces a risk-aware autonomous agent framework for digital nuclear control rooms, enhancing safety by integrating real-time cognitive state inference with probabilistic safety assessments.

Contribution

It presents a novel risk constrained agent runtime that couples cognitive inference with safety assessment, enabling proactive, human-centered autonomy in nuclear operations.

Findings

Demonstrated ability to predict cognitive degradation in a digital control room simulator.

Effectively constrained unsafe autonomous recommendations in real time.

Provided risk-aware guidance while maintaining human decision authority.

Abstract

The rapid digitization of nuclear power plant main control rooms has fundamentally reshaped operator interaction patterns, introducing complex soft-control behaviors and elevated cognitive risks that are not adequately addressed by existing human reliability analysis approaches. Although recent advances in large language models and autonomous agents offer new opportunities for intelligent decision support, their deployment in safety critical environments remains constrained by risks of hallucinated reasoning and weakened human authority. This study proposes NuHF Claw, a persistent cognitive-risk agent framework that enables risk governed human centered autonomy for digital nuclear operations. The core methodological innovation lies in the introduction of a risk constrained agent runtime, which tightly couples cognitive state inference with probabilistic safety assessment to regulate autonomous system behavior in real time. By integrating cognitively grounded workload and situational awareness estimation with dynamic human error probability prediction, the framework transforms conventional offline reliability analysis into a proactive intervention mechanism embedded directly within operational workflows. Experimental validation on a high-fidelity digital control room simulator demonstrates that NuHF Claw can anticipate interface induced cognitive degradation, dynamically constrain unsafe autonomous recommendations, and provide risk-aware navigational guidance while preserving human decision authority. The results highlight a fundamental shift from automation-driven operation toward cognition-aware autonomy, offering a principled pathway for the safe integration of intelligent agents into next-generation nuclear control environments.