Designing an agentic AI workflow for structured information extraction from scientific text: A case study on atomic layer deposition of ZnO and IGZO
Open Access
- 30 April 2026
- journal article
- Published by American Vacuum Society in Journal of Vacuum Science & Technology A
- Vol. 44 (3)
Abstract
The rapid growth of scientific literature in materials sciences and other domains presents a growing challenge where critical process knowledge remains embedded in unstructured text, limiting its reuse for data-driven discovery. Agentic workflows, which integrate large language models (LLMs) with different tools, such as application programming interfaces (APIs), and rule-based functions, have emerged as a promising paradigm to overcome these limitations. In this work, we introduce SciKGExtract, an agentic artificial intelligence (AI) workflow for structured knowledge extraction from scientific publications. The workflow combines LLM-based contextual understanding with deterministic tools for schema validation, data cleaning, and normalization, leveraging authoritative external repositories such as PubChem to ensure accuracy and semantic consistency. Applied to atomic layer deposition (ALD) literature from the AtomicLimits database, SciKGExtract produces a structured dataset capturing experimental parameters and material properties across test cases of zinc oxide (ZnO) and indium-gallium-zinc oxide (IGZO). The extracted data reveal dominant ALD methods and chemistries, variability in reported growth-per-cycle and temperature ranges, and the need for richer metadata to enable reliable cross-study comparisons. These results demonstrate how structured extraction can transform unstructured literature into AI-ready knowledge, accelerating validation, benchmarking, and discovery in emerging materials systems.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/T026138/1)
- Intel Corporation
- Merck KGaA
- KISSKI AI Service Center (BMBF, Grant ID: 01IS22093C)
This publication has 32 references indexed in Scilit:
- LLM-based AI agents for automated extraction of material properties and structural featuresComputational Materials Science, 2026
- Impact of atomic layer deposition supercycle design on the reliability of heterogenous IGZO channel TFTsCeramics International, 2024
- Extracting structured information from unstructured histopathology reports using generative pre‐trained transformer 4 ( GPT ‐4)The Journal of Pathology, 2023
- Evolution of number of citations per article in Materials Science: possible causes and effect on the impact factor of journalsScientometrics, 2023
- Exploration of Chemical Composition of In–Ga–Zn–O System via PEALD Technique for Optimal Physical and Electrical PropertiesAdvanced Electronic Materials, 2023
- The carbon and hydrogen contents in ALD-grown ZnO films define a narrow ALD temperature windowVacuum, 2021
- ZnO Thin Films Grown by Plasma‐Enhanced Atomic Layer Deposition: Material Properties Within and Outside the “Atomic Layer Deposition Window”Physica Status Solidi (a), 2019
- Remote plasma enhanced atomic layer deposition of ZnO for thin film electronic applicationsMicroelectronic Engineering, 2012
- Low-temperature atomic layer deposition of ZnO thin films: Control of crystallinity and orientationThin Solid Films, 2011
- The rate of growth in scientific publication and the decline in coverage provided by Science Citation IndexScientometrics, 2010