Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI
Abstract
Extracting knowledge from large databases of experimental materials data requires repeated analyses and reusable records of their choices and results. We developed Multi-Agentic AI (MAA), a multi-agent system in which AI agents with distinct roles analyze experimental thermoelectric data under predefined instructions and quality checks, saving analysis records traceable to their sources. In four experiments varying theme and cycle counts, we measured what accumulated in these records. In the largest experiment (100 analyses across 10 themes and 10 cycles), concept co-occurrences were concentrated within themes, vocabulary was shared across themes and some relation descriptions were first detected in later cycles. A specialized AI that searches this experiment's knowledge bases and reads their analysis records answered materials questions with cited sources. Retrospective checks, including tracing an answer generated with a preliminary corpus back to the source data, exposed errors: traceability makes errors findable but not absent.
Related
- Physics-Informed and Knowledge-Driven Generative AI for Autonomous Discovery of Porous Oxide Energy Materials: Opportunities and Challenges
- From Autonomous Knowledge Generation to Generalizable Property Prediction: A Precision-First Pipeline for Electro-Optic Materials Discovery
- Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials
- Tribocharging of Granular Materials Dictated by Geometric and Thermoelectric Effects
- Specialized machine learning force fields for materials dynamics
BibTeX
@misc{hashimoto2026autonomous,
title = {{Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI}},
author = {Yusuke Hashimoto and Takaaki Tomai},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00627},
eprint = {2611.00627},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00627},
}
RIS
TY - UNPB
TI - Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI
AU - Yusuke Hashimoto
AU - Takaaki Tomai
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00627
UR - https://arxiv.org/abs/2611.00627
AB - Extracting knowledge from large databases of experimental materials data requires repeated analyses and reusable records of their choices and results. We developed Multi-Agentic AI (MAA), a multi-agent system in which AI agents with distinct roles analyze experimental thermoelectric data under predefined instructions and quality checks, saving analysis records traceable to their sources. In four experiments varying theme and cycle counts, we measured what accumulated in these records. In the largest experiment (100 analyses across 10 themes and 10 cycles), concept co-occurrences were concentrated within themes, vocabulary was shared across themes and some relation descriptions were first detected in later cycles. A specialized AI that searches this experiment's knowledge bases and reads their analysis records answered materials questions with cited sources. Retrospective checks, including tracing an answer generated with a preliminary corpus back to the source data, exposed errors: traceability makes errors findable but not absent.
ER -