SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41375-41376
DOI: 10.1609/aaai.v40i48.42275 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Alexander Sachuk und 2 weiteren Autor:innen.
Abstract (Originalsprache)
The management and annotation of complex, multi-modal scientific data remains a major obstacle for AI-driven research due to poor reusability and scalability of current solutions. We propose SciDataMAS, a novel LLM-powered multi-agent system (MAS), which automate scientific data management through a structured data lake with provenance-based organization and an adaptive metadata taxonomy. The system uses specialized workflows for automated dataset creation, data insertion and retrieval. Experiments show the system's proficiency, with modern LLMs like GPT-5 successfully generating rich metadata schemas and filling them with high accuracy. This work provides a foundational step towards fully automated, reusable, and scalable scientific data organization which may lead to generation and accumulation by scientific community well annotated AI-ready datasets.
Zitieren
APA
Sachuk, A., Chukanov, V., & Pchitskaya, E. (2026). SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41375-41376. https://doi.org/10.1609/aaai.v40i48.42275
Vancouver
Sachuk A, Chukanov V, Pchitskaya E. SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41375-41376. doi:10.1609/aaai.v40i48.42275
BibTeX
@article{Sachuk2026,
author = {Sachuk, Alexander and Chukanov, Vyacheslav and Pchitskaya, Ekaterina},
title = {SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41375--41376},
doi = {10.1609/aaai.v40i48.42275}
}
EUVIMED