用大模型动态模拟多人协作中的认知负荷，提升人因可靠性数据精度。
A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs
- 基于微调大模型，按场景实时模拟操作员行为与负荷。
- 在高温气冷堆场景中，预测准确率优于现有商用方法。
- 无需专家输入，适合大规模、高精度人因数据采集。
人因可靠性分析（HRA）数据对推动方法发展至关重要。然而，现有数据收集方法缺乏足够粒度，多数无法捕捉动态特征，且常需专家输入，导致耗时费力。为此，我们提出一种自动化HRA数据采集新范式，聚焦人类失误背后的关键指标——协作环境下的工作负荷。本研究引入一种新型情景驱动的工作负荷估计方法，利用微调的大语言模型（LLMs）实现。通过在高温气冷堆（HTGRs）真实运行数据上训练LLMs，我们实现了在多种协作场景下对操作员行为与认知负荷的实时模拟。该方法能动态适应负荷变化，提供更精准、灵活且可扩展的负荷评估。结果表明，所提出的WELLA（Workload Estimation with LLMs and Agents）在预测准确率上优于现有商业级基于LLM的方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。