自动完成文献综述全流程，让科研决策更高效。
AutoSynthesis: An agentic system for automated meta-analysis
- 多智能体协作自动完成检索、筛选、数据提取等步骤
- 处理28项研究，提取20条以上定量数据，结果与人工分析接近
- 输出符合PRISMA标准的透明报告，适合研究者与政策制定者
证据综合对科学、医学、教育和政策等领域至关重要，但量化证据综合仍主要依赖人工且难以扩展。本文提出AutoSynthesis，一个端到端的多智能体系统，可自动完成元分析全过程：输入自然语言研究问题后，系统自动生成检索策略，获取文献，筛选候选研究，评估全文纳入资格，提取定量统计量，计算标准化效应量，并进行随机效应元分析。系统还支持异质性分析与偏倚风险评估。输出为符合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多个定量结论，其汇总效应估计值与专家手工元分析的Hedges' g高度一致，表明自动化方法能有效实现可扩展的量化证据综合，助力跨领域循证决策。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。