Metraipolis › archive › dc_6db401bb568c

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis — arXiv:2610.20538

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20538
License (as archived)
CC0-1.0
Archived
2026-10-15T14:23:55.948Z
SHA-256 of the archived text
aeb990b4358ae52ec1652e3f43d20e4d028ac71fc25a4b87eaa022b9bde8a1f7
Stable URL of this page
https://metraipolis.com/documento/dc_6db401bb568c

How to cite

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis — arXiv:2610.20538 — arXiv (en), https://arxiv.org/abs/2610.20538 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6db401bb568c (Metraipolis archive dc_6db401bb568c, sha256 aeb990b4358ae52ec1652e3f43d20e4d028ac71fc25a4b87eaa022b9bde8a1f7)
BibTeX
@misc{dc6db401bb568c,
  title = {PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis — arXiv:2610.20538},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20538},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6db401bb568c; sha256 aeb990b4358ae52ec1652e3f43d20e4d028ac71fc25a4b87eaa022b9bde8a1f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20538. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning, as models are increasingly asked to produce charts, webpages, animations, and semi-structured documents. Recently, proprietary models have pushed far ahead, producing interactive artifacts even from a text description or a screenshot alone. Yet their data and training remain closed, and open progress is held back by the quantity and quality of available data and by the pipelines and methods for producing it. Quality is the harder of the two, since a sample must be correct as a program, well built, and above all visually right once rendered. No existing signal covers all three. Execution often returns just a pass or fail, code similarity does not map to the visual output, and task-specific verifiers do not generalize. To push open progress further, we start from the data side with PrismaForge, a hierarchical data pipeline centered on a synthesized rubric that decomposes these factors into checkable criteria. The same rubric serves as both filter and reward: it curates the supervised corpus, then drives reinforcement learning on visual-coding tasks. Leveraging PrismaForge for data synthesis and filtering, we build PrismaCoder-2M, the most diverse open dataset for multimodal code intelligence and the largest to date. On the model side, we train PrismaCoder-9B and PrismaCoder-35B on this data and release both. They lead the open state of the art by a wide margin and rival leading proprietary systems. Our analyses further show that the proposed rubric-based pipeline improves multimodal coding performance across model backbones. We release our code and data at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.20538 — 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 2026-10-15T13:53:35.982Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).