Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

TL;DR

Manalyzer is an innovative multi-agent system that automates the entire meta-analysis process, reducing human effort and addressing hallucination issues in data extraction and paper screening, validated on a comprehensive multi-domain benchmark.

Contribution

This work introduces Manalyzer, the first end-to-end automated meta-analysis system leveraging multi-agent collaboration and tool calls to improve accuracy and efficiency.

Findings

Manalyzer outperforms LLM baseline in meta-analysis tasks.

Constructed a benchmark with 729 papers and 10,000+ data points.

Achieves significant performance improvements in multi-modal data extraction.

Abstract

Meta-analysis is a systematic research methodology that synthesizes data from multiple existing studies to derive comprehensive conclusions. This approach not only mitigates limitations inherent in individual studies but also facilitates novel discoveries through integrated data analysis. Traditional meta-analysis involves a complex multi-stage pipeline including literature retrieval, paper screening, and data extraction, which demands substantial human effort and time. However, while LLM-based methods can accelerate certain stages, they still face significant challenges, such as hallucinations in paper screening and data extraction. In this paper, we propose a multi-agent system, Manalyzer, which achieves end-to-end automated meta-analysis through tool calls. The hybrid review, hierarchical extraction, self-proving, and feedback checking strategies implemented in Manalyzer significantly alleviate these two hallucinations. To comprehensively evaluate the performance of meta-analysis, we construct a new benchmark comprising 729 papers across 3 domains, encompassing text, image, and table modalities, with over 10,000 data points. Extensive experiments demonstrate that Manalyzer achieves significant performance improvements over the LLM baseline in multi meta-analysis tasks. Project page: https://black-yt.github.io/meta-analysis-page/ .