D2: An LLM agent driving end-to-end visual AI modeling in energy platforms
Yu Li, Qiaoqiao Zhao, Min Hou, Quansheng Bai, Xiyan Zou, Changle Xie, Chang Shu, Boyang Ma, LI Zhi-jin · Energy and AI · 2025
This study presents X-AI, a domain-native, agent-driven, and end-to-end modeling platform developed to support digital transformation in the energy sector. X-AI integrates advanced Machine Learning (ML) and Deep Learning (DL) capabilities into a workflow-driven environment that enables energy engineers to construct and deploy predictive models without prior AI expertise. A key innovation is the introduction of Dragon Dawn (D2), an intelligent agent powered by Large Language Models (LLMs) and agent-based reasoning. D2 interprets natural language instructions, retrieves domain-relevant knowledge, orchestrates modeling workflows, and guides multi-step optimization processes, thereby lowering technical barriers and cognitive load for users. To quantitatively evaluate platform usability, a novel metric termed Cognitive-Operation Efficiency Ratio (COER) is proposed, capturing both task efficiency and cognitive effort. Experimental evaluation shows that D2 significantly enhances modeling productivity, with over eightfold improvement in COER. A real-world case study on inflow forecasting in cascade hydropower systems validates the platform’s capabilities. By comparing LSTM and D2-assisted XGBoost models, the study demonstrates how the agent facilitates iterative reasoning, feature enhancement, and hyperparameter tuning. These findings establish X-AI as a practical, scalable AI solution for accelerating intelligent decision-making in the energy domain.