Metraipolis › archive › dc_02082fa041bb

OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells — arXiv:2609.37773

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37773
License (as archived): CC0-1.0
Archived: 2026-10-07T16:24:09.677Z
SHA-256 of the archived text: 0419ac42ab38518e242a52df1acd66219248699750b3d53a9f4b71a353b9b212
Stable URL of this page: https://metraipolis.com/documento/dc_02082fa041bb

How to cite

OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells — arXiv:2609.37773 — arXiv (en), https://arxiv.org/abs/2609.37773 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02082fa041bb (Metraipolis archive dc_02082fa041bb, sha256 0419ac42ab38518e242a52df1acd66219248699750b3d53a9f4b71a353b9b212)

BibTeX

@misc{dc02082fa041bb,
  title = {OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells — arXiv:2609.37773},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37773},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02082fa041bb; sha256 0419ac42ab38518e242a52df1acd66219248699750b3d53a9f4b71a353b9b212},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37773. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial Intelligence Virtual Cells (AIVCs) are envisioned as scientific agents that simulate cellular responses, explain underlying mechanisms, and support hypothesis-driven discovery. Existing AIVC benchmarks, however, operate primarily at the simulation layer, motivating complementary evaluation of how models interpret experimental evidence and formulate biological hypotheses. We introduce OmniVCBench, a figure-centric, source-traceable benchmark for the interpretation component of an AIVC. It contains 6,077 curated single- and multi-subfigure question--answer pairs derived from figures and experimental contexts in the scientific literature. Guided by Bloom's taxonomy, we instantiate interpretation-layer counterparts of the AIVC Predict--Explain--Discover agenda through three scientific reasoning tasks. We further introduce AIVC-Judge, a task-conditioned MLLM-as-a-judge framework with category-specific, reference-aware rubrics for evaluating open-ended responses. A complementary Model-Derived Hard-Negative Mining (MDHNM) strategy converts plausible errors observed during model inference into MCQ distractors for lower-cost evaluation. Within the evaluated heterogeneous model pool, MCQ accuracy correlates positively with AIVC-Judge scores, providing a complementary view of performance alongside open-response evaluation. Code and data demo are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2609.37773 — 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 2026-10-07T15:54:53.656Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).