AutoSynthesis: An agentic system for automated meta-analysis

• URL: http://arxiv.org/abs/2607.15247v1
• Date: Thu, 16 Jul 2026 17:45:27 GMT
• Title: AutoSynthesis: An agentic system for automated meta-analysis
• Abstract summary: We introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis.<n>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.
• Score: 29.353490196463138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis [10.0612384634729]
  AutoForest is an end-to-end system that generates publication-ready forest plots directly from biomedical papers.<n>Given one or more study papers, AutoForest automatically suggests ICO (Intervention, Comparator, Outcome) elements, extracts outcome data, performs statistical synthesis, and renders the final forest plot.
  arXiv  Detail & Related papers  (2026-06-01T15:49:33Z)
• AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature [55.66036140125613]
  This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers.<n>AgentCAT serves as an alternative to overcome the long-standing data bottleneck in chemical engineering field.
  arXiv  Detail & Related papers  (2026-02-10T04:30:11Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• ASBench: Image Anomalies Synthesis Benchmark for Anomaly Detection [32.99680725493585]
  Anomaly detection plays a pivotal role in manufacturing quality control, yet its application is constrained by limited abnormal samples and high manual annotation costs.<n>We propose ASBench, the first comprehensive benchmarking framework dedicated to evaluating anomaly synthesis methods.
  arXiv  Detail & Related papers  (2025-10-09T08:23:29Z)
• Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System [48.093356587573666]
  Meta-analysis is a systematic research methodology that synthesizes data from multiple existing studies to derive comprehensive conclusions.<n>Traditional meta-analysis involves a complex multi-stage pipeline including literature retrieval, paper screening, and data extraction.<n>We propose a multi-agent system, Manalyzer, which achieves end-to-end automated meta-analysis through tool calls.
  arXiv  Detail & Related papers  (2025-05-22T07:25:31Z)
• Transforming Evidence Synthesis: A Systematic Review of the Evolution of Automated Meta-Analysis in the Age of AI [0.3441021278275805]
  Automated Meta-analysis is powered by natural language processing and machine learning.<n>Findings reveal a predominant focus on automating data processing (57%), while only 17% address advanced synthesis stages.<n>Despite recent breakthroughs in large language models (LLMs) and advanced AI, integration into statistical modeling and higher-order synthesis remains underdeveloped.
  arXiv  Detail & Related papers  (2025-04-28T00:40:17Z)
• Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis [7.059964549363294]
  This study investigates the automation of meta-analysis in scientific documents using large language models (LLMs) Our research introduces a novel approach that fine-tunes the LLM on extensive scientific datasets to address challenges in big data handling and structured data extraction.
  arXiv  Detail & Related papers  (2024-11-16T20:18:57Z)
• SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation [55.2480439325792]
  We study the synthesis of six datasets, covering topic classification, sentiment analysis, tone detection, and humor. We find that SynthesizRR greatly improves lexical and semantic diversity, similarity to human-written text, and distillation performance.
  arXiv  Detail & Related papers  (2024-05-16T12:22:41Z)
• ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining [56.15126714863963]
  ChemMiner is an end-to-end framework for extracting chemical data from literature.<n>ChemMiner incorporates three specialized agents: a text analysis agent for coreference mapping, a multimodal agent for non-textual information extraction, and a synthesis analysis agent for data generation.<n> Experimental results demonstrate reaction identification rates comparable to human chemists while significantly reducing processing time, with high accuracy, recall, and F1 scores.
  arXiv  Detail & Related papers  (2024-02-20T13:21:46Z)
• Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3 [52.59930033705221]
  We present a dataset of 11,644 entities extracted from 1,137 papers, resulting in 268 papers with at least one complete seed-mediated gold nanorod growth procedure and outcome for a total of 332 complete procedures. We present a dataset of 11,644 entities extracted from 1,137 papers, resulting in papers with at least one complete seed-mediated gold nanorod growth procedure and outcome for a total of 332 complete procedures.
  arXiv  Detail & Related papers  (2023-04-26T22:21:33Z)
• PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text [1.9573380763700712]
  This dataset simultaneously contains the synthesis sentences extracted from the experimental paragraphs, as well as the entity mentions and intra-sentence relations. A two-step human annotation and inter-annotator agreement study guarantee the high quality of the PcMSP corpus. We introduce four natural language processing tasks: sentence classification, named entity recognition, relation classification, and joint extraction of entities and relations.
  arXiv  Detail & Related papers  (2022-10-22T09:43:54Z)
• BeCAPTCHA-Type: Biometric Keystroke Data Generation for Improved Bot Detection [63.447493500066045]
  This work proposes a data driven learning model for the synthesis of keystroke biometric data. The proposed method is compared with two statistical approaches based on Universal and User-dependent models. Our experimental framework considers a dataset with 136 million keystroke events from 168 thousand subjects.
  arXiv  Detail & Related papers  (2022-07-27T09:26:15Z)
• RetroXpert: Decompose Retrosynthesis Prediction like a Chemist [60.463900712314754]
  We devise a novel template-free algorithm for automatic retrosynthetic expansion. Our method disassembles retrosynthesis into two steps. While outperforming the state-of-the-art baselines, our model also provides chemically reasonable interpretation.
  arXiv  Detail & Related papers  (2020-11-04T04:35:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.