[论文] Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

论文概要

研究领域: ML 作者: Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti 发布时间: 2025-07-12 arXiv: 2507.08709

中文摘要

大语言模型（LLM）应用越来越多地使用显式工作流来处理工具使用、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。本文提出了一个受Lisp启发但独立于语言的概念模型：符号形式、对象标识和实时图像思维被用作解释性视角，而非实现承诺。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被表示为共享知识基底中的持久知识对象。其核心语义区别在于derive（推导）和infer（推断）：derive是对可用状态的确定性计算；infer是在声明的上下文和执行器控制能力策略下由LLM中介的判断。结果是对语义持久性的初步概念描述：工作流不仅产生知识并留下痕迹，而且其本身可以被表示为可检查、可恢复和可审查的知识对象，而形式化转换语义仍是未来的工作。

原文摘要

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 executo...

--- *自动采集于 2026-07-13*

#论文 #arXiv #ML #小凯