A Vision for a Logic-Based Workflow Formulation Framework and an Agentic Execution Pipeline for Pattern Engineering

2026-10-02

AI Summary

This study addresses the absence of a general principled framework for schema engineering workflows and the difficulty existing systems face in composably representing schema operations. To overcome these limitations, this work proposes a typed logic-based workflow framework. By defining typed representations of fixed components, the approach translates schema operations into composable query chains, thereby decoupling workflow definitions from execution constraints. Furthermore, it designs an LLM agent-driven execution pipeline to enable automated analysis. Experiments conducted on the WIPO dataset successfully execute three categories of query tasks, including exemplar mining. The results validate performance variations across different LLM configurations alongside their error localization capabilities. Ultimately, this research establishes a modular and orchestrable paradigm for schema engineering.

Abstract

Organizations increasingly depend on insights drawn from data to inform consequential decisions. Many concern structural behaviors, which we call patterns. Producing them may require working with multiple pattern types, performing different operations over them, and composing those operations into workflows, an activity we call pattern engineering. No principled framework exists for organizing such workflows: analysts devise each by hand, and existing systems automate particular analytical objectives rather than representing pattern operations in a general, composable form. We introduce a typed framework that represents each pattern through a fixed set of modular components, and expresses pattern operations as queries which specify input and output components. Chaining queries composes workflows, while execution of any individual query remains unconstrained. We instantiate the framework with an LLM-based agentic executor and evaluate example-mining, example-alignment, and pattern-induction queries over two temporal patterns, using World Intellectual Property Organization (WIPO) reports and patent data. All three queries are carried out across four LLM settings, which perform differently by target component, while the traces allow us to localize errors by execution stage.

Problem

• pattern engineering
• workflow formulation
• structural patterns
• composable operations
• data-driven decision making

Innovation

• Pattern Engineering
• Logic-Based Framework
• Agentic Execution Pipeline
• Large Language Models
• Composable Workflows