大型语言模型 (LLM) 应用程序越来越多地使用显式工作流程来进行工具使用, 检索, 分支, 检查点, 和人工审批。现有的工作流系统已经解决了许多执行问题。本文提出了一种受 Lisp 启发但与语言无关的概念模型: 符号形式, 对象标识, 和实时图像思维用作解释性镜头, 而不是实现承诺。在此模型中，, 工作流定义, 工作流实例, 推理记录, 上下文快照, 和依赖关系表示为共享知识基础中的持久知识对象。其核心语义区别在于导引和推断之间:导引是对可用状态的确定性计算;推断是在声明的上下文和执行者控制的能力策略下调解LLM判断。结果是语义持久性:工作流的初步概念说明，工作流不仅产生知识并留下痕迹,，而且本身可以表示为可检查,、可恢复,和可审查的知识对象,，而正式转换语义仍然是未来的工作。
Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow definitions, workflow instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects in a shared knowledge substrate. Its central semantic distinction is between derive and infer: derive is deterministic computation over available state; infer is mediated LLM judgment under declared context and executor-controlled capability policy. The result is a preliminary conceptual account of semantic persistence: workflows do not merely produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and reviewable knowledge objects, while formal transition semantics remain future work.
科目: 人工智能 (cs.AI); 编程语言 (cs.PL); 软件工程 (cs.SE)
Subjects: Artificial Intelligence (cs.AI); Programming Languages (cs.PL); Software Engineering (cs.SE)