Agentic scientific visualization generation and caption semantic alignment
Information Visualization · 2026-07 · 25 (3) · 213-231
DOI: 10.1177/14738716261434841 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Visualization, online erschienen am 05.04.2026. Verfasst von Xuyi Lu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Youth Fund of Computer Network Information Center of Chinese Academy of Sciences, National Natural Science Foundation of China.
Abstract (Originalsprache)
In the era of data-intensive scientific discovery, visualization serves as a crucial cognitive tool for researchers, while captions that align with visuals are essential for accurately conveying scientific intent. However, current scientific visualization workflows face significant challenges, including high technical barriers and semantic misalignment among user intent, visual output, and textual descriptions. To address these issues, this paper proposes SciVis-AGE, a visual analytics system based on multi-agent collaboration. Its core methodologies comprise an agent-based task decomposition and operator encapsulation approach for automatic visualization generation, and a multi-agent triangular debate mechanism for semantic alignment and caption optimization. The system effectively reduces the technical burden on domain experts and, through iterative debate among Intent Guardian, Visual Verifier, and Annotation Checker agents, ensures precise alignment of generated images and captions with user intent, visual content, and highlighted features, thereby enhancing the rigor and efficiency of scientific communication.
Förderung
- Youth Fund of Computer Network Information Center of Chinese Academy of Sciences
- National Natural Science Foundation of China
Zitieren
APA
Lu, X., Li, G., Dong, Y., Peng, R., Wang, Z., Tian, D., & Shan, G. (2026). Agentic scientific visualization generation and caption semantic alignment. Information Visualization, 25(3), 213-231. https://doi.org/10.1177/14738716261434841
Vancouver
Lu X, Li G, Dong Y, Peng R, Wang Z, Tian D, et al. Agentic scientific visualization generation and caption semantic alignment. Information Visualization. 2026;25(3):213-231. doi:10.1177/14738716261434841
BibTeX
@article{Lu2026,
author = {Lu, Xuyi and Li, Guan and Dong, Yu and Peng, Ruixiao and Wang, Zhe and Tian, Dong and Shan, Guihua},
title = {Agentic scientific visualization generation and caption semantic alignment},
journal = {Information Visualization},
year = {2026},
volume = {25},
number = {3},
pages = {213--231},
doi = {10.1177/14738716261434841}
}
EUVIMED