MetaSyn is a stage-level benchmark of 442 meta-analyses showing LLM agents retrieve up to 90.9% of eligible studies but include at most 52.7% in their final reports.
Marshall and Byron C
2 Pith papers cite this work, alongside 644 external citations. Polarity classification is still indexing.
2
Pith papers citing it
644
external citations · OpenAlex
years
2026 2representative citing papers
Agentic AI in engineering and manufacturing is currently most useful for structured repetitive work and data tasks, but adoption is limited by fragmented data, regulatory constraints, legacy systems, and needs for verification and human oversight.
citing papers explorer
-
MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio
MetaSyn is a stage-level benchmark of 442 meta-analyses showing LLM agents retrieve up to 90.9% of eligible studies but include at most 52.7% in their final reports.
-
Agentic AI in Engineering and Manufacturing: Industry Perspectives on Utility, Adoption, Challenges, and Opportunities
Agentic AI in engineering and manufacturing is currently most useful for structured repetitive work and data tasks, but adoption is limited by fragmented data, regulatory constraints, legacy systems, and needs for verification and human oversight.