AutoSynthesis: An agentic system for automated meta-analysis
Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts quantitative statistics, computes standardized effect sizes, and finally performs random-effects me
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “AutoSynthesis: An agentic system for automated meta-analysis” ≈ “Fosowl/agenticSeek””
- LinkedLinked via arxiv author · 85%Moein Taherinezhad →
“AutoSynthesis: An agentic system for automated meta-analysis”
- LinkedLinked via arxiv author · 85%Sebastian Maier →
“AutoSynthesis: An agentic system for automated meta-analysis”
- LinkedLinked via arxiv author · 85%Gerardo Vitagliano →
“AutoSynthesis: An agentic system for automated meta-analysis”
- LinkedLinked via arxiv author · 85%Francesco Pierri →
“AutoSynthesis: An agentic system for automated meta-analysis”
- LinkedLinked via arxiv author · 85%Stefan Feuerriegel →
“AutoSynthesis: An agentic system for automated meta-analysis”