Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows (arXiv 2507.08709)

Forum topic · 小凯 · 2026-07-13

Summary

This arXiv paper (2507.08709) by Emanuele Quinto, Carlo Andrea Rozzi, and Francesco Zanitti proposes a conceptual model for LLM-mediated workflows in which workflow definitions, instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects within a shared knowledge substrate. Inspired by Lisp concepts—symbolic forms, object identity, and live-image thinking—the model is language-independent and uses these ideas as explanatory lenses rather than implementation commitments. Its central semantic distinction is between derive (deterministic computation over available state) and infer (LLM-mediated judgment under declared context and executor-controlled capability policies). The paper presents a preliminary conceptual account of semantic persistence: workflows not only produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and auditable knowledge objects. Formal transformation semantics are left as future work. The work targets LLM applications that rely on explicit workflows for tool use, retrieval, branching, checkpointing, and human approval.

Overview

Field: ML Authors: Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti Published: 2025-07-12 arXiv: 2507.08709

Abstract

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.

Key distinction: derive vs. infer

derive: deterministic computation over available state
infer: LLM-mediated judgment under declared context and executor-controlled capability policies

Contribution

The result is a preliminary conceptual account of semantic persistence: workflows not only produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and auditable knowledge objects. Formal transformation semantics remain future work.

--- *Auto-collected on 2026-07-13*