Agentic schema-guided extraction of materials process knowledge from scientific literature
Abstract
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic verification provide complementary controls for converting complex materials literature into reusable, machine-actionable experimental knowledge.
Related
- Agentic programs: an emerging form of scientific software in computational materials science
- ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature
- Mined from Scientific Literature: Process Schemas for Atomic Layer Deposition and Etching in Materials Science
- Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI
- Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
BibTeX
@misc{sadruddin2026agentic,
title = {{Agentic schema-guided extraction of materials process knowledge from scientific literature}},
author = {Sameer Sadruddin and Jennifer D'Souza},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06322},
eprint = {2610.06322},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.06322},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Agentic schema-guided extraction of materials process knowledge from scientific literature
AU - Sameer Sadruddin
AU - Jennifer D'Souza
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.06322
UR - https://arxiv.org/abs/2610.06322
AB - Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic verification provide complementary controls for converting complex materials literature into reusable, machine-actionable experimental knowledge.
ER -