Two new research papers detail the development of automated pipelines for systematic reviews and meta-analyses using multiple AI agents. The first, LUMEN, automates six phases of the process, achieving directional agreement with published meta-analyses at a cost of $19-$29 per review. It highlights that while multi-agent designs improve data extraction, they can hinder screening. The second system, meta-pipe, integrates a complete workflow including manuscript generation and overclaim detection, with an estimated API cost of $15-$30 per review. Both systems emphasize the feasibility of AI-assisted evidence synthesis, with meta-pipe noting that formal validation is still underway. AI
IMPACT These systems demonstrate the potential for AI to significantly reduce the time and cost of evidence synthesis in scientific research.
RANK_REASON Two academic papers published on arXiv describing new AI systems for systematic reviews and meta-analyses.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
