Engineering LLM-native software remains a challenging and immature field. Current practice is largely exploratory, relying on experimentation and heuristic techniques such as prompting and context engineering. These, however, are low-level and lack the principled structure needed to support design-level reasoning or analysis. In contrast, traditional software engineering leverages modularity and abstraction to communicate and analyze system behavior. To bring similar rigor to LLM-native development, we propose methods for documenting generative flows and for stating properties of LLM-based software designs. Such methods must account for the stochastic, prompt-dependent behavior of large language models while remaining expressive enough to capture emergent phenomena. Our initial approach is based on graphical probabilistic models, tailored to capture phenomena characteristic of LLM-native systems. This framework -- what we term Generation Networks -- aims to provide a foundation for principled reasoning about generative interactions and system-level properties in LLM-centric software architectures.

翻译：工程化LLM原生软件仍是一个充满挑战且不成熟的领域。当前实践主要依赖探索性方法，通过提示工程和上下文工程等实验性启发式技术。但这些方法层次较低，缺乏支持设计层面推理或分析所需的原则性结构。相比之下，传统软件工程利用模块化和抽象化来沟通和分析系统行为。为将类似严谨性引入LLM原生开发，我们提出了记录生成流及阐述基于LLM的软件设计属性的方法。此类方法需兼顾大语言模型的随机性与提示依赖性，同时保持足够的表现力以捕捉涌现现象。我们的初步方法基于图概率模型，专门针对LLM原生系统的特征现象进行建模。该框架（我们称之为"生成网络"）旨在为以LLM为中心的软件架构中生成交互与系统级属性的原则性推理奠定基础。