# Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

arXiv: https://arxiv.org/abs/2607.08740 · HTML: https://mlsanity.com/paper/2607.08740/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 40 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Recursive Language Models](https://mlsanity.com/paper/2512.24601/) (2025)
- [PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows](https://mlsanity.com/paper/2508.02866/) (2025)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation](https://mlsanity.com/paper/2407.02742/) (2024)
- [LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology](https://mlsanity.com/paper/2509.13978/) (2025)
- [Pel, A Programming Language for Orchestrating AI Agents](https://mlsanity.com/paper/2505.13453/) (2025)
- [AgentSPEX: An Agent SPecification and EXecution Language](https://mlsanity.com/paper/2604.13346/) (2026)
- [From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop](https://mlsanity.com/paper/2506.10021/) (2025)

## Abstract (arXiv)

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.