PERELMAN: Pipeline for scientific literature meta-analysis
Daniil Sherki, Daniil Merkulov, Aleksandra Savina, Dzhantemir Kikov, Dmitry Parpulov, Alexander Ivanov, Artem Abakumov, Ekaterina Muravleva
Abstract
We present PERELMAN (PipEline foR sciEntific Literature Meta-ANalysis), an agentic framework designed to extract specific information from a large corpus of scientific articles to support large-scale literature reviews and meta-analyses. Our central goal is to reliably transform heterogeneous article content into a unified, machine-readable representation. PERELMAN first elicits domain knowledge-including target variables, inclusion criteria, units, and normalization rulesсthrough a structured dialogue with a subject-matter expert. This domain knowledge is then reused across multiple stages of the pipeline and guides coordinated agents in extracting evidence from narrative text, tables, and figures, enabling consistent aggregation across studies. In order to assess reproducibility and validate our implementation, we evaluate the system on the task of reproducing the meta-analysis of layered Li-ion cathode properties NMC811 reported in [Savina and Abakumov, 2023]. We describe our solution, which has the potential to reduce the time required to prepare meta-analyses from months to minutes.
BibTeX
@inproceedings{ijcai2026_perelmanpipeline,
title = {PERELMAN: Pipeline for scientific literature meta-analysis},
author = {Daniil Sherki and Daniil Merkulov and Aleksandra Savina and Dzhantemir Kikov and Dmitry Parpulov and Alexander Ivanov and Artem Abakumov and Ekaterina Muravleva},
booktitle = {IJCAI 2026},
year = {2026}
}