English: With the high-penetration integration of renewable energy and the increasing complexity of energy systems, traditional methods for modeling, optimization, and fault diagnosis are facing challenges such as multi-source heterogeneous data fusion, operational uncertainty, complex failure mechanisms, and the need for real-time decision-making. Large language models (LLMs) and autonomous agents provide new paradigms for knowledge understanding, task decomposition, model generation, optimization decision-making, and anomaly diagnosis in energy systems. This track focuses on the application of trustworthy large-model agents in low-carbon energy systems. It highlights key issues including the fusion of physical mechanisms with data-driven modeling, operational optimization, fault diagnosis, digital twins, human-machine collaborative decision-making, and safety verification, aiming to promote the deep integration of artificial intelligence with power and renewable energy systems.

中文: 随着可再生能源高比例接入和能源系统复杂度提升，传统建模、优化与故障诊断方法面临多源异构数据融合、运行状态不确定、故障机理复杂和实时决策等挑战。大模型与自主智能体为能源系统知识理解、任务分解、模型生成、优化决策和异常诊断提供了新范式。本专题聚焦可信大模型智能体在低碳能源系统中的应用，重点讨论机理知识融合、数据驱动建模、运行优化、故障诊断、数字孪生、人机协同决策及安全可信验证等关键问题，促进人工智能技术与电力及可再生能源系统的深度融合。