Agentic architecture automates research-question-to-workflow translation via LLM intent extraction, deterministic generators, and Skills, raising intent accuracy from 44% to 83% and cutting data transfer by 92% in a 1000 Genomes evaluation.
In: 2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation
Agentic architecture automates research-question-to-workflow translation via LLM intent extraction, deterministic generators, and Skills, raising intent accuracy from 44% to 83% and cutting data transfer by 92% in a 1000 Genomes evaluation.