发表机构
University of Piraeus; Örebro University; NCSR “Demokritos”（比雷埃夫斯大学; 厄勒布鲁大学; 希腊国家科学研究中心“德谟克利特”）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出genRTEC方法，利用预训练LLM从自然语言描述生成可执行的MAS规范（RTEC语言），支持复杂层次与循环依赖，实证表明高预测准确性且不牺牲推理效率。
AI 中文摘要
多智能体系统（MAS）规范表达了智能体及其环境动作的效果，以及其他时间现象，例如智能体执行动作的时间间隔。MAS规范还应该是可执行的，以便进行运行时监控。构建MAS规范需要形式语言专业知识，而机器学习技术依赖于很少可用的标注数据。为解决这些问题，我们提出了'genRTEC'，一种利用预训练大型语言模型（LLMs）从自然语言描述生成可执行MAS规范的方法，该规范使用'运行时事件演算'（RTEC）语言。genRTEC仅基于所涉及概念的简短自然语言描述，就能构建具有复杂层次和循环依赖关系的MAS规范。我们对genRTEC进行了广泛的实证评估，涵盖了各种MAS规范，包括定性和定量评估。我们的结果表明，genRTEC构建的可执行MAS规范具有高预测准确性，且不牺牲推理效率。
英文摘要
MAS specifications express the effects of the actions of the agents and their environment, as well as other temporal phenomena, such as the intervals during which an agent may perform an action. The specification of a MAS should also be executable in order to allow for run-time monitoring. Constructing the specification of a MAS requires formal language expertise, while machine learning techniques depend on labelled data which are rarely available. To address these issues, we propose `genRTEC', a method that leverages pre-trained Large Language Models (LLMs) to generate executable MAS specifications, in the language of the `Run-Time Event Calculus' (RTEC), from natural language descriptions. genRTEC constructs MAS specifications with complex hierarchical and cyclic dependencies based only on short natural language descriptions of the concepts involved. We present an extensive empirical evaluation of genRTEC, spanning various MAS specifications, including both a qualitative and a quantitative assessment. Our results demonstrate that genRTEC constructs executable MAS specifications of high predictive accuracy without compromising reasoning efficiency.
