IEA-Plugin: An AI Agent Reasoner for Test Data Analytics
Seoyeon Kim, Yu Su, Li-C. Wang
TL;DR
IEA-Plugin addresses the challenges of capturing diverse engineering requirements and scaling backend analytics by turning user queries into structured workflows and distilled API specifications. The approach combines an ICL-centric workflow reasoner, a retrieval-augmented AI agent with explicit thought, and a dedicated Data agent, all orchestrated on LangGraph to enable industrial deployment. Key contributions include automatic initial query generation, accumulation of query-workflow pairs for knowledge acquisition, and automatic distillation into a stable API structure that decouples frontend queries from backend implementation. The work demonstrates that embracing variability in LLM outputs and focusing on a principled planning process can yield robust, scalable analytics pipelines for test data analytics. Overall, IEA-Plugin provides a practical pathway to scalable, knowledge-driven backend tooling in engineering contexts.
Abstract
This paper introduces IEA-plugin, a novel AI agent-based reasoning module developed as a new front-end for the Intelligent Engineering Assistant (IEA). The primary objective of IEA-plugin is to utilize the advanced reasoning and coding capabilities of Large Language Models (LLMs) to effectively address two critical practical challenges: capturing diverse engineering requirements and improving system scalability. Built on the LangGraph agentic programming platform, IEAplugin is specifically tailored for industrial deployment and integration with backend test data analytics tools. Compared to the previously developed IEA-Plot (introduced two years ago), IEA-plugin represents a significant advancement, capitalizing on recent breakthroughs in LLMs to deliver capabilities that were previously unattainable.