Agentic iteration improves perceived quality of generated multiview genomics visualizations over direct LLM generation, but adding more specialist agents or a reviewer yields no further gains across 159 test cases.
Borkin, and Nils Gehlenborg
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Sycamore shows grounding synthetic personas with real-user artifacts aligns their feedback language and concerns more closely with experts, yet both synthetic conditions miss experts' image-modality preference and converge on a find-and-adapt evaluation frame.
YAC is a prototype system that uses a tool-calling multi-agent architecture to translate natural language into linked interactive visualizations and filters for biomedical data, with user-adjustable structured output and a domain-expert user study.
citing papers explorer
-
YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery
YAC is a prototype system that uses a tool-calling multi-agent architecture to translate natural language into linked interactive visualizations and filters for biomedical data, with user-adjustable structured output and a domain-expert user study.