Summary
AutoSynthesis is an end-to-end multi-agent AI system for automated meta-analysis, introduced by researchers including Moein Taherinezhad and Stefan Feuerriegel (arXiv:2607.15247, cs.AI). Given a natural-language research question, the system automatically formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts quantitative statistics, computes standardized effect sizes, and performs random-effects meta-analysis. It also supports heterogeneity analysis and risk-of-bias assessment, and outputs transparent reports aligned with PRISMA guidelines. In an applied case, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims; its pooled effect estimates closely matched the Hedges' g values from expert-conducted manual meta-analyses, indicating strong agreement with human evidence synthesis. The results suggest that agentic AI systems can make quantitative evidence synthesis scalable, supporting evidence-based decision-making across science, medicine, education, and policy.
Paper Overview
Field: cs.AI
Authors: Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel
Published: 2026-07-16
arXiv:
2607.15247Abstract
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. This paper introduces 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
- 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, the system produces a transparent report aligned with PRISMA guidelines.
In the paper's application, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims. The pooled effect estimates produced by the system are similar to the 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.
---
*Source: arXiv:2607.15247, collected 2026-07-20*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178446936