{
  "id": 11345,
  "url": "https://arxiv.org/abs/2607.15247v1",
  "title": "AutoSynthesis: An agentic system for automated meta-analysis",
  "summary": "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",
  "authors": "Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel",
  "category": "research",
  "topics": "regulation,children-education,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-16T17:45:27.000Z",
  "fetched_at": "2026-07-18T05:10:55.931Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/11345",
  "original_url": "https://arxiv.org/abs/2607.15247v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}