Yingchen Zhang

Submitted: 18 September 2026 Posted: 20 September 2026 You are already at the latest version Large language model (LLM) agents can learn through interaction with external environments, obtain training signals and reusable experience from task execution. Scaling this form of learning requires a sufficient supply of interactive environments and tasks grounded in those environments, with explicit objectives and completion criteria.

Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assistants, unsafe content in these agents can propagate through persistent state, reusable skills, and tool-mediated interactions, creating a substantially larger semantic attack surface.

1. Introduction With the continuous development of the power industry and the demand for clean, low-carbon, and green development, renewable energy represented by hydropower has developed rapidly [1,2,3]. Among them, variable-speed pumped storage units (VSPSUs) based on doubly fed induction motors and pump turbines (PTs) have become a research hotspot in recent years due to their advantages of large capacity, high operating efficiency, and flexible power adjustment [4,5,6].