Metraipolis › archive › dc_661d2c422cfc

Validation-Gated ML Pipeline Synthesis with Expert-Grounded Self-Evolving Skills — arXiv:2611.04180

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04180
License (as archived)
CC0-1.0
Archived
2026-11-04T12:27:42.549Z
SHA-256 of the archived text
a4b7598d27ef81947439f9562ef0610809eb1944e5a52ce95493edd4d90a002a
Stable URL of this page
https://metraipolis.com/documento/dc_661d2c422cfc

How to cite

Validation-Gated ML Pipeline Synthesis with Expert-Grounded Self-Evolving Skills — arXiv:2611.04180 — arXiv (en), https://arxiv.org/abs/2611.04180 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_661d2c422cfc (Metraipolis archive dc_661d2c422cfc, sha256 a4b7598d27ef81947439f9562ef0610809eb1944e5a52ce95493edd4d90a002a)
BibTeX
@misc{dc661d2c422cfc,
  title = {Validation-Gated ML Pipeline Synthesis with Expert-Grounded Self-Evolving Skills — arXiv:2611.04180},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04180},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_661d2c422cfc; sha256 a4b7598d27ef81947439f9562ef0610809eb1944e5a52ce95493edd4d90a002a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04180. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in large language models have enabled agentic systems that automate machine learning pipeline construction from minimal user input. However, existing agentic AutoML methods either depend on rigid templates that limit adaptability, target narrow task domains, or rely on free-form code generation that lacks reliability guarantees, leaving intermediate errors to propagate silently and degrade the final model. We present EvoML, an agentic framework for end-to-end ML pipeline synthesis built on expert-grounded skills that evolve across runs, executed through a validation-gated harness. The framework decomposes pipeline construction into four phases coordinated by three agents: an Orchestrator that enforces validation gates, advancing each phase only when its outputs pass structural, execution, and semantic checks, which precludes error propagation and keeps every artifact auditable; an Executor that runs expert-grounded skills, grounded in the nnU-Net workflow and pairing reusable templates with online adaptation; and a Curator that performs post-run evolution, consolidating the scripts and guidance recovered during a run into the skill library so it improves across datasets. We evaluate EvoML on eight datasets spanning six sophisticated, real-world ML task types, against agentic AutoML systems and command-line coding tools. EvoML achieves full automation and the best final model quality on all eight, spanning segmentation (up to 0.94 Dice), classification (0.99 accuracy), reconstruction (0.95 SSIM), and denoising (0.79 normalized PSNR), while transferring to broader ML tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.04180 — 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 2026-11-04T12:26:47.130Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).