AutoSynthesis: An agentic system for automated meta-analysis
For researchers and policymakers needing scalable evidence synthesis, AutoSynthesis automates a traditionally manual and time-consuming process, though it is an incremental application of existing multi-agent and meta-analysis methods.
AutoSynthesis is an end-to-end multi-agent system that automates the entire meta-analysis pipeline, from search strategy formulation to random-effects meta-analysis. In testing, it screened over 28 studies and extracted more than 20 quantitative claims, producing pooled effect estimates closely matching expert-conducted meta-analyses (similar Hedges' g).
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 meta-analysis. AutoSynthesis further supports heterogeneity analysis to examine how effect sizes vary across moderators, as well as risk-of-bias assessment. As output, AutoSynthesis produces a transparent report aligned with PRISMA guidelines. In our application, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims. The pooled effect estimates produced by AutoSynthesis are similar to Hedges' $g$ of expert-conducted meta-analyses, indicating close agreement with manual evidence synthesis. Together, these results show that AutoSynthesis can make quantitative evidence synthesis more scalable, thereby supporting evidence-based decision-making across disciplines.