LUMEN: Cost-Transparent Multi-Agent Pipeline for Automated Systematic Review and Meta-Analysis
arXiv:2606.28362v1 Announce Type: cross Abstract: Systematic reviews and meta-analyses (SR/MA) remain the gold standard for evidence synthesis, yet completing one typically requires 67 weeks and substantial expert effort. Recent large language model (LLM) systems have demonstrated strong performance on individual SR phases - screening (otto-SR: 96.7% sensitivity), extraction (Gartlehner et al.: 91.0% accuracy), and search (TrialMind: 0.83 recall) - but no study has reported what it actually costs to run an end-to-end pipeline, how cost distributes across phases, or how architectural choices af
LLM systems have recently demonstrated strong performance on individual components of systematic reviews, making an end-to-end cost analysis timely and necessary to understand deployment feasibility.
This development provides critical insight into the economic viability and scalability of AI-driven automation for complex, knowledge-intensive tasks like systematic reviews, which are foundational for evidence-based decision-making.
The transparency into cost distribution and architectural impacts on automated systematic reviews will enable more efficient design and adoption of AI agents in research, potentially democratizing access to comprehensive evidence synthesis.
- · AI agent developers
- · Research institutions
- · Pharmaceutical companies
- · Publishing platforms
- · Manual systematic review services
- · Inefficient research workflows
Researchers gain access to significantly faster and potentially more affordable systematic reviews and meta-analyses.
Reduced barriers to evidence synthesis lead to an acceleration of scientific discovery and evidence-based policy making across various fields.
The demonstrated cost-efficiency of integrated AI agent pipelines could drive broader adoption of similar 'workflow collapse' solutions in other white-collar sectors.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI