# A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs

arXiv: https://arxiv.org/abs/2502.00022 · HTML: https://mlsanity.com/paper/2502.00022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 51 references that are in the map.
- First posted on arXiv 16 Jan 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [Can Large Language Model Agents Simulate Human Trust Behavior?](https://mlsanity.com/paper/2402.04559/) (2024)
- [Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents](https://mlsanity.com/paper/2402.12327/) (2024)
- [Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency](https://mlsanity.com/paper/2407.09519/) (2024)
- [Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs](https://mlsanity.com/paper/2402.08189/) (2024)
- [Adapting LLM Agents with Universal Feedback in Communication](https://mlsanity.com/paper/2310.01444/) (2023)
- [DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser](https://mlsanity.com/paper/2311.16565/) (2023)
- [Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention](https://mlsanity.com/paper/2305.00262/) (2023)
- [KRAIL: A Knowledge-Driven Framework for Base Human Reliability Analysis Integrating IDHEAS and Large Language Models](https://mlsanity.com/paper/2412.18627/) (2024)
- [A Hybrid Real-Time Framework for Efficient Fussell-Vesely Importance Evaluation Using Virtual Fault Trees and Graph Neural Networks](https://mlsanity.com/paper/2412.10484/) (2024)

## Abstract (arXiv)

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.