Metraipolis › archive › dc_1ff2adf3565c

VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair — arXiv:2610.02399

Source
arXiv
Original
https://arxiv.org/abs/2610.02399
License (as archived)
CC0-1.0
Archived
2026-10-05T23:09:01.942Z
SHA-256 of the archived text
e291f4cff92ca870acc1bcecfcd82803695c6363aff7982b6a5f3522a5b822cc
Stable URL of this page
https://metraipolis.com/documento/dc_1ff2adf3565c

How to cite

VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair — arXiv:2610.02399 — arXiv, https://arxiv.org/abs/2610.02399 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1ff2adf3565c (Metraipolis archive dc_1ff2adf3565c, sha256 e291f4cff92ca870acc1bcecfcd82803695c6363aff7982b6a5f3522a5b822cc)
BibTeX
@misc{dc1ff2adf3565c,
  title = {VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair — arXiv:2610.02399},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02399},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1ff2adf3565c; sha256 e291f4cff92ca870acc1bcecfcd82803695c6363aff7982b6a5f3522a5b822cc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02399. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal agents are increasingly used for data visualization tasks but remain limited in autonomous review. Unlike humans, they may fail to recognize when a visualization is incorrect, determine what to change, repair it without disrupting correct content, and verify whether the intervention succeeded. Existing benchmarks largely evaluate predefined individual capabilities such as chart generation, instruction-guided editing, or defect detection, and therefore do not capture this gap in autonomous review. We introduce VisAudit, a benchmark for evaluating visualization diagnosis, repair, and verification. Given a rendered chart and configurable auxiliary evidence, including its source data table, intended text summary, and visualization code, an agent iteratively diagnoses potential defects, modifies and executes visualization code, inspects execution and visual feedback, and determines when no further intervention is needed. VisAudit defines three tracks spanning diagnosed repair, autonomous repair, and open-world verification, and contains 1,900 flawed instances across 21 chart types and 10 flaw categories, together with 300 initially correct charts. We construct the benchmark through controlled perturbations of validated source visualizations, with systematic verification and human-aligned quality control to ensure that injected defects are well-defined and recoverable from the available evidence. Experiments with leading multimodal models reveal a substantial gap from reliable autonomous review: the strongest evaluated model fully recovers only $47.4\%$ of flawed charts in the autonomous-repair setting.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02399 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T23:01:38.576Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).