# AutoSynthesis: An agentic system for automated meta-analysis

arXiv: https://arxiv.org/abs/2607.15247 · HTML: https://mlsanity.com/paper/2607.15247/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [Automated Paper Screening for Clinical Reviews Using Large Language Models](https://mlsanity.com/paper/2305.00844/) (2023)
- [A Meta-Analysis of the Persuasive Power of Large Language Models](https://mlsanity.com/paper/2512.01431/) (2025)
- [Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse](https://mlsanity.com/paper/2602.18710/) (2026)
- [What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction](https://mlsanity.com/paper/2507.15152/) (2025)
- [LatteReview: A Multi-Agent Framework for Systematic Review Automation Using Large Language Models](https://mlsanity.com/paper/2501.05468/) (2025)
- [Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis](https://mlsanity.com/paper/2411.10878/) (2024)
- [Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System](https://mlsanity.com/paper/2505.20310/) (2025)
- [The Agentic Garden of Forking Paths](https://mlsanity.com/paper/2607.01507/) (2026)
- [Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews](https://mlsanity.com/paper/2603.22327/) (2026)
- [Automated reproducibility assessments in the social and behavioral sciences using large language models](https://mlsanity.com/paper/2606.13670/) (2026)

## Built on by (most cited first, 2 of 2)

- [Reward Hacking Challenges Oversight of Autonomous Research Agents](https://mlsanity.com/paper/2609.28614/) (2026)
- [Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research](https://mlsanity.com/paper/2609.35089/) (2026)

## Abstract (arXiv)

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.