自动合成：一种用于自动化元分析的智能系统

中文摘要 AI 辅助

证据合成对于将原始研究转化为科学、医学、教育和政策方面可靠的知识至关重要。然而，定量证据合成在很大程度上仍然是人工操作且难以扩展。在此，我们介绍了自动合成，一个用于自动化元分析的端到端多智能体系统。给定自然语言的研究问题，它能制定搜索策略、检索科学文献、筛选候选研究、评估全文适用性、提取定量统计数据、计算标准化效应量，最后进行随机效应元分析。它还支持异质性分析和偏倚风险评估，并生成符合PRISMA指南的透明报告。在我们的应用中，它筛选了超过28项研究并提取了20多条定量声明。其合并效应估计与专家进行的元分析的Hedges' $g$ 相似，表明与人工证据合成高度一致。这些结果表明自动合成可使定量证据合成更具扩展性，从而支持跨学科的循证决策。

英文摘要

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.

发表机构

• Politecnico di Milano（米兰理工大学）
• LMU Munich（慕尼黑大学）
• Munich Center for Machine Learning（慕尼黑机器学习中心）
• MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

机构由 AI 辅助整理，请以论文原文为准。