AutoSynthesis: An agentic system for automated meta-analysis

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel
• Venue: arXiv: cs.AI
• Published: 2026-07-16
• Collected: 2026-07-17
• URL: http://arxiv.org/abs/2607.15247v1
• PDF: https://arxiv.org/pdf/2607.15247v1
• DOI: UNKNOWN

Plain-Language Brief

AutoSynthesis is a multi-agent system designed to automate meta-analysis, making it easier and scalable for turning primary research into reliable knowledge in various fields like science, medicine, education, and policy.

What the Document Says

• The paper introduces AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis.
• AutoSynthesis accepts a research question in natural language and performs various tasks such as formulating search strategies, retrieving scientific literature, screening candidate studies, assessing full-text eligibility, extracting quantitative statistics, computing standardized effect sizes, performing random-effects meta-analysis, and heterogeneity analysis.
• The system also supports risk-of-bias assessment and produces a transparent report aligned with PRISMA guidelines.
• In the 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.
• This indicates close agreement between automated and manual evidence synthesis.

Key Concepts Mentioned

• AutoSynthesis
• meta-analysis
• quantitative evidence synthesis
• research question
• PRISMA guidelines

Claims Made by the Document

• AutoSynthesis can make quantitative evidence synthesis more scalable.
• The pooled effect estimates produced by AutoSynthesis are similar to Hedges' $g$ of expert-conducted meta-analyses.

Evidence Used

• 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.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.