Manual information extraction for systematic reviews (SRs) is a major, time-consuming bottleneck that limits the efficiency and reliability of evidence synthesis.

We present REACT-ExtrAct, a retrieval-augmented, agent-based framework that combines Small Language Models with heuristicguided reasoning to automate data extraction while ensuring source transparency. Evaluated on two published systematic reviews, our system outperformed Naive RAG and Iter-RetGen baselines in factual accuracy, completeness, and traceability.

By enabling lightweight, local deployment, React-ExtrAct offers a trustworthy and sustainable alternative to Large Language Model pipelines for SR automation.

S. Krawczyk, P. Jemioło, J. Karkowski, I. Ivanoska, M. Mirchev, W. Kusa, ReAct-ExtrAct: A Tool for Source-Grounded Automated Data Extraction in Systematic Reviews, 2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL) (2025) 340-343.