Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti
• Venue: arXiv: cs.AI
• Published: 2026-07-09
• Collected: 2026-07-10
• URL: http://arxiv.org/abs/2607.08740v1
• PDF: https://arxiv.org/pdf/2607.08740v1
• DOI: UNKNOWN

Plain-Language Brief

The paper proposes a conceptual model for large language model (LLM) applications that use explicit workflows. The model is designed to represent various elements of the workflow such as definitions, instances, and dependency relations as persistent knowledge objects in a shared knowledge substrate.

What the Document Says

• The paper discusses LLM applications using explicit workflows for tasks like tool use, retrieval, branching, checkpointing, and human approval.
• Existing workflow systems have solutions for execution concerns.
• A Lisp-inspired but language-independent conceptual model is proposed with symbolic forms, object identity, and live-image thinking as explanatory lenses, not implementation commitments.
• In this model, various elements of the workflow are represented as persistent knowledge objects: definitions, instances, inference records, context snapshots, and dependency relations.
• The central semantic distinction is between derive (deterministic computation) and infer (mediated LLM judgment).
• The proposed model aims to make workflows inspectable, resumable, and reviewable knowledge objects.
• Formal transition semantics are considered as future work.

Key Concepts Mentioned

• Large Language Model (LLM)
• Workflow
• Symbolic Forms
• Object Identity
• Live-Image Thinking
• Derive
• Infer

Claims Made by the Document

• The proposed model can represent workflows as persistent knowledge objects.
• The model distinguishes between derive and infer.

Evidence Used

• Existing text within the paper

Methods / Approach

• Proposing a conceptual model for LLM applications with explicit workflows

Limitations Stated by the Authors

Formal transition semantics are considered as future work.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The paper does not provide details on the implementation or testing of the proposed model.

Open Questions

• How will the formal transition semantics be defined in the future?
• What is the practical application and effectiveness of this model?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper provides a conceptual account but does not delve into details about implementation or testing.

Raw Abstract / Excerpt

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.