Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System
This work addresses the time-consuming and error-prone nature of traditional meta-analysis for researchers, though it is incremental as it builds on existing LLM-based methods with specific enhancements.
The authors tackled the problem of automating meta-analysis by proposing Manalyzer, a multi-agent system that uses strategies like hybrid review and hierarchical extraction to reduce hallucinations in paper screening and data extraction, achieving significant performance improvements over LLM baselines on a new benchmark of 729 papers with over 10,000 data points.
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/ .