Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
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 knowle
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%antoinezambelli/forge →
- PossiblePossibly related (embedding) · 54%llmsresearch/llm-flashcards →
- PossiblePossibly related (embedding) · 53%langgenius/dify →
- PossiblePossibly related (embedding) · 53%Pipelex/pipelex →
- PossiblePossibly related (embedding) · 52%Rheosoph/flow-like →
- PossiblePossibly related (embedding) · 53%kennethlaw325/awesome-llm-knowledge-systems →
- LinkedLinked via arxiv author · 85%Emanuele Quinto →
“Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows”
- LinkedLinked via arxiv author · 85%Carlo Andrea Rozzi →
“Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows”