证据综合对于将初级研究转化为科学, 医学, 教育, 和政策的可靠知识至关重要。然而, 定量证据合成仍然主要是手动的并且难以扩展。在这里,我们介绍AutoSynthesis,一个用于自动荟萃分析的端到端多代理系统。给定自然语言的研究问题, AutoSynthesis 制定搜索策略, 检索科学文献, 筛选候选研究, 评估全文资格, 提取定量统计数据, 计算标准化效应大小, 最后执行随机效应荟萃分析。 AutoSynthesis 进一步支持异质性分析，以检查效果大小如何随调节者, 变化以及偏倚风险评估。作为输出, AutoSynthesis 会生成符合 PRISMA 准则的透明报告。在我们的应用, AutoSynthesis 中筛选了超过 28 项研究并提取了 20 多项定量声明。 AutoSynthesis 产生的汇总效应估计与专家进行的荟萃分析, 的 Hedges $g$ 类似，表明与手动证据合成非常一致。 , 这些结果共同表明，AutoSynthesis 可以使定量证据合成更具可扩展性,，从而支持跨学科的基于证据的决策。
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.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)