Metraipolis › archive › dc_f3bc54c0ffa4

Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering — arXiv:2608.29016

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29016
License (as archived)
CC0-1.0
Archived
2026-10-17T08:59:39.677Z
SHA-256 of the archived text
883e4b3b6968fa6088c94c9b8385c7669b4e1167392182b7eb767d873aa8da91
Stable URL of this page
https://metraipolis.com/documento/dc_f3bc54c0ffa4

How to cite

Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering — arXiv:2608.29016 — arXiv (en), https://arxiv.org/abs/2608.29016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3bc54c0ffa4 (Metraipolis archive dc_f3bc54c0ffa4, sha256 883e4b3b6968fa6088c94c9b8385c7669b4e1167392182b7eb767d873aa8da91)
BibTeX
@misc{dcf3bc54c0ffa4,
  title = {Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering — arXiv:2608.29016},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29016},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3bc54c0ffa4; sha256 883e4b3b6968fa6088c94c9b8385c7669b4e1167392182b7eb767d873aa8da91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; however, they remain limited when applied to complex, domain-specific tasks such as medical image processing. General-purpose models lack explicit domain knowledge and robust validation mechanisms to ensure correctness, often requiring substantial human intervention to produce reliable processing pipelines. To address these limitations, we propose AutoMedImg, a multi-agent framework for fully automated medical image processing code generation. AutoMedImg orchestrates specialised agents across two phases: a Planning Phase that performs dataset analysis and architecture design with semantic and formal verification, and a Coding Phase that generates modules in parallel with static checking, execution testing, and assembly validation. This multi-stage validation mitigates error propagation throughout generation, while comprehensive auto-context engineering combining domain-specific knowledge bases, shared memory, and validation feedback automates context construction without manual prompting. A cross-project adaptive pipeline synthesis mechanism further accumulates validated pipelines and retrieves proven components for new tasks based on project similarity, enhancing generation efficiency through cross-project learning. Extensive evaluation across six diverse and well-established medical imaging datasets with five backbone LLMs demonstrates that AutoMedImg achieves zero human intervention, with Dice scores of up to 0.90 for segmentation tasks and 99% accuracy for classification.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in cs.SE).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.29016 — 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 2026-10-17T08:37:02.093Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).