A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs
This addresses the need for more efficient and accurate HRA data collection in multi-agent collaborative environments, such as high-temperature gas-cooled reactors, though it is incremental as it builds on existing LLM-based approaches.
The paper tackled the problem of collecting granular and dynamic Human Reliability Analysis (HRA) data by proposing an automated method using fine-tuned large language models (LLMs) to simulate human behavior and estimate workload in collaborative scenarios, resulting in outperforming existing commercial LLM-based methods in prediction accuracy.
HRA (Human Reliability Analysis) data is crucial for advancing HRA methodologies. however, existing data collection methods lack the necessary granularity, and most approaches fail to capture dynamic features. Additionally, many methods require expert knowledge as input, making them time-consuming and labor-intensive. To address these challenges, we propose a new paradigm for the automated collection of HRA data. Our approach focuses on key indicators behind human error, specifically measuring workload in collaborative settings. This study introduces a novel, scenario-driven method for workload estimation, leveraging fine-tuned large language models (LLMs). By training LLMs on real-world operational data from high-temperature gas-cooled reactors (HTGRs), we simulate human behavior and cognitive load in real time across various collaborative scenarios. The method dynamically adapts to changes in operator workload, providing more accurate, flexible, and scalable workload estimates. The results demonstrate that the proposed WELLA (Workload Estimation with LLMs and Agents) outperforms existing commercial LLM-based methods in terms of prediction accuracy.