PERELMAN: Pipeline for scientific literature meta-analysis. Technical report

TL;DR

PERELMAN is a framework that automates large-scale scientific literature meta-analyses by extracting and unifying data from diverse articles, significantly reducing review time.

Contribution

It introduces a structured dialogue-based approach to encode domain knowledge and guides agents to extract evidence, enabling efficient, reproducible meta-analyses.

Findings

Successfully reproduces meta-analysis of NMC811 cathode properties

Reduces meta-analysis preparation time from months to minutes

Demonstrates reliable extraction and aggregation of heterogeneous data

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 rules-through 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 material). We describe our solution, which has the potential to reduce the time required to prepare meta-analyses from months to minutes.