SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)

Alexander Sachuk; Vyacheslav Chukanov; Ekaterina Pchitskaya

AAAI 2026technical0 citations

SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)

Alexander Sachuk, Vyacheslav Chukanov, Ekaterina Pchitskaya

Abstract

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

BibTeX

@inproceedings{aaai2026_scidatamasllmdri,
  title = {SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)},
  author = {Alexander Sachuk and Vyacheslav Chukanov and Ekaterina Pchitskaya},
  booktitle = {AAAI 2026},
  year = {2026}
}