让工作流变成可检查、可恢复的知识对象，提升LLM应用的可追溯性。
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
- 用符号形式与对象身份建模工作流，使其成为持久知识
- 区分确定性推导与大模型判断，明确执行边界
- 适合关注LLM应用可解释性与流程复现的研究者
大型语言模型（LLM）应用越来越多地采用显式工作流来管理工具调用、信息检索、分支决策、检查点保存和人工审批。现有工作流系统已解决许多执行问题。本文提出一种受Lisp启发但语言无关的概念模型：符号形式、对象身份与实时思维作为解释框架，而非实现承诺。在此模型中，工作流定义、实例、推理记录、上下文快照及依赖关系均被表示为共享知识基底中的持久知识对象。其核心语义区分在于‘推导’与‘推理’：推导是基于已有状态的确定性计算；推理是在声明上下文与执行者控制的能力策略下进行的LLM判断。结果是初步的概念性描述：工作流不仅生成知识并留下痕迹，本身也可作为可检查、可恢复、可审查的知识对象存在，而形式化转换语义仍为未来工作。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。