Entity · paper

Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

paperactiveprovisionalworkflow-as-knowledge-semantic-persistence-for-llm-mediated-workflows-9e4eaacb·1 events·first seen 3d ago

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

More like this (12)

Dynamic Workflows LMs as Task-Specific Knowledge Bases: An Interpretability Analysis semi-structured knowledge bases Knowledge-Augmented Tool Execution Mistral Workflows Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning Always-OnAgents: A Survey of Persistent Memory, State, and Governance in LLM Agents human-LLM collaborative annotation Learned Semantic Transform When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing A sleep-like consolidation mechanism for LLMs

Recent events (1)

4arXiv · cs.AI·3d ago·source ↗

Semantic persistence model for LLM workflows as inspectable knowledge objects

A new arXiv preprint proposes a conceptual model for treating LLM workflow components — definitions, instances, inference records, context snapshots — as persistent, inspectable knowledge objects in a shared substrate. The framework draws on Lisp-inspired ideas (symbolic forms, object identity, live-image thinking) as explanatory lenses rather than implementation commitments. A central distinction is drawn between 'derive' (deterministic computation) and 'infer' (LLM-mediated judgment under declared context), with formal transition semantics left as future work. The work addresses a gap in how agentic workflow systems represent and reason about their own execution state.

Agent and Tool Ecosystem Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows