ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI

TL;DR

Problem: enterprise Agentic AI suffers from a reusability dilemma and structural hallucinations when reusing legacy workflows across platforms. Approach: ReusStdFlow introduces an Extraction-Storage-Construction paradigm that decomposes DSLs into standardized modular segments, stores them in a dual-knowledge graph+vector repository, and assembles workflows via retrieval-augmented generation. Contributions: standardized segmentation method, hybrid storage, retrieval-augmented construction, and empirical validation on 200 n8n workflows achieving >90% accuracy. Impact: enables scalable reuse of enterprise digital assets, reduces redesign costs, and improves logical/topological integrity of automated workflows.

Abstract

To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs heterogeneous, platform-specific Domain Specific Languages (DSLs) into standardized, modular workflow segments. It employs a dual knowledge architecture-integrating graph and vector databases-to facilitate synergistic retrieval of both topological structures and functional semantics. Finally, workflows are intelligently assembled using a retrieval-augmented generation (RAG) strategy. Tested on 200 real-world n8n workflows, the system achieves over 90% accuracy in both extraction and construction. This framework provides a standardized solution for the automated reorganization and efficient reuse of enterprise digital assets.

Figures (3)

• Figure 1: Overall architecture of the ReusStdFlow framework.
• Figure 2: Flowchart of the entire process illustrated by a case study of electricity bill interpretation.
• Figure 3: Screenshot of the ReusStdFlow interface.