AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI

TL;DR

AgentSLR demonstrates that large language models can fully automate systematic literature reviews in epidemiology, significantly reducing time and maintaining high accuracy, thus accelerating evidence synthesis.

Contribution

This paper introduces an open-source agentic AI pipeline that automates the entire systematic review process, achieving human-level performance in epidemiology.

Findings

Reduces review time from 7 weeks to 20 hours

Performance depends on model capabilities rather than size

Identifies key failure modes through human validation

Abstract

Systematic literature reviews are essential for synthesizing scientific evidence but are costly, difficult to scale and time-intensive, creating bottlenecks for evidence-based policy. We study whether large language models can automate the complete systematic review workflow, from article retrieval, article screening, data extraction to report synthesis. Applied to epidemiological reviews of nine WHO-designated priority pathogens and validated against expert-curated ground truth, our open-source agentic pipeline (AgentSLR) achieves performance comparable to human researchers while reducing review time from approximately 7 weeks to 20 hours (a 58x speed-up). Our comparison of five frontier models reveals that performance on SLR is driven less by model size or inference cost than by each model's distinctive capabilities. Through human-in-the-loop validation, we identify key failure modes. Our results demonstrate that agentic AI can substantially accelerate scientific evidence synthesis in specialised domains.