[论文] AutoSynthesis: An agentic system for automated meta-analysis

论文概要

研究领域: cs.AI 作者: Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel 发布时间: 2026-07-16 arXiv: 2607.15247

中文摘要

证据综合对于将原始研究转化为科学、医学、教育和政策领域的可靠知识至关重要。然而，定量证据综合目前仍主要依赖人工操作，难以规模化。本文提出 AutoSynthesis，一个端到端的多智能体自动元分析系统。给定自然语言表述的研究问题，AutoSynthesis 会自动制定检索策略、检索科学文献、筛选候选研究、评估全文合格性、提取定量统计数据、计算标准化效应量，最后执行随机效应元分析。此外，系统还支持异质性分析（检验效应量如何随调节变量变化）以及偏倚风险评估。输出方面，AutoSynthesis 生成符合 PRISMA 指南的透明报告。在实际应用中，AutoSynthesis 筛选了超过 28 项研究，提取了 20 多条定量主张。其汇总的效应估计与专家手动元分析的 Hedges' g 高度接近，表明与人工证据综合具有高度一致性。这些结果表明，AutoSynthesis 能够使定量证据综合更具可扩展性，从而支持跨学科的循证决策。

原文摘要

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.

--- *自动采集于 2026-07-20*

#论文 #arXiv #AI #小凯