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 models (LLM) applications that use workflows. This model represents various elements of the workflow, such as definitions, instances, and dependencies, as persistent knowledge objects in a shared substrate. The central distinction is between 'derive' (deterministic computation) and 'infer' (mediated LLM judgment). The goal is to make workflows inspectable, resumable, and reviewable as knowledge objects.

What the Document Says

• The paper discusses a conceptual model for LLM applications with workflows.
• The model uses symbolic forms, object identity, and live-image thinking.
• Workflow definitions, instances, records, snapshots, and dependencies are represented as persistent knowledge objects.
• The central distinction is between 'derive' (deterministic computation) and 'infer' (mediated LLM judgment).
• The goal is to represent workflows as inspectable, resumable, and reviewable knowledge objects.

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 is language-independent.
• Workflows can be represented as persistent knowledge objects.

Evidence Used

• The use of 'Lisp-inspired' suggests a language-independent approach.
• The description of workflow definitions, instances, etc., as persistent knowledge objects.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

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.