发表机构
Faculty of Applied Mathematics and Informatics, University of Osijek Croatia; Meet Intelligent Innovations LLC（奥西耶克大学应用数学与信息学院，克罗地亚; Meet智能创新有限责任公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究如何在实时交互环境中控制大语言模型智能体行为，提出分层场景驱动的LLM控制框架，通过结构化提示实现运行时行为控制，在ARDena中实现该框架并评估，结果显示场景驱动提示能有效控制LLM智能体。
AI 中文摘要
大语言模型（LLMs）催生了能力日益强大的对话智能体，但在实时交互环境中可靠控制其行为仍是重大挑战。现有方法常依赖难以适应变化交互需求的模型微调或对齐程序。本文引入分层场景驱动的LLM控制框架，通过结构化提示实现运行时行为控制。结合持久上下文与特定场景约束，该方法可在不改变基础模型的情况下修改智能体行为。在实时多模态具身智能体ARDena中实现该框架，评估其控制有效性、响应延迟和操作稳定性。结果表明，仅场景定义就能产生显著不同的交互行为，同时保持稳定实时操作，凸显场景驱动提示对控制LLM智能体的有效性。
英文摘要
Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive environments remains a significant challenge. Existing approaches often rely on model fine-tuning or alignment procedures that are difficult to adapt to changing interaction requirements. This paper introduces layered scenario-driven LLM control, a framework that enables runtime behavior control through structured prompting. By combining persistent context with scenario-specific constraints, the approach allows agent behavior to be modified during interaction without changing the underlying model. The framework is implemented in ARDena, a real-time multimodal embodied agent that integrates speech interaction, visual perception, tool use, and avatar-based response generation. The proposed approach is evaluated with respect to control effectiveness, response latency, and operational stability. The results demonstrate that scenario definitions alone can produce substantially different interaction behaviors while maintaining stable real-time operation, highlighting the effectiveness of scenario-driven prompting for controlling LLM agents.
Comments12 pages, 3 figures
