Metraipolis › archive › dc_99e54bf64e75

TuiML: Machine Learning for AI Agents — arXiv:2609.17984

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.17984
License (as archived): CC0-1.0
Archived: 2026-10-15T15:07:53.029Z
SHA-256 of the archived text: 0ee213cea1ac322cec6676427685b63fb8660bccd2b823328f7236780ff511a8
Stable URL of this page: https://metraipolis.com/documento/dc_99e54bf64e75

How to cite

TuiML: Machine Learning for AI Agents — arXiv:2609.17984 — arXiv (en), https://arxiv.org/abs/2609.17984 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99e54bf64e75 (Metraipolis archive dc_99e54bf64e75, sha256 0ee213cea1ac322cec6676427685b63fb8660bccd2b823328f7236780ff511a8)

BibTeX

@misc{dc99e54bf64e75,
  title = {TuiML: Machine Learning for AI Agents — arXiv:2609.17984},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17984},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99e54bf64e75; sha256 0ee213cea1ac322cec6676427685b63fb8660bccd2b823328f7236780ff511a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17984. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by recalling APIs from memory and writing code, an approach that hides what a library offers, delays errors until runtime, and loses experimental state between turns. We present TuiML, a self-contained machine-learning library built for AI agents, with native algorithms across supervised, unsupervised, time-series, data handling, tuning, and evaluation tasks. Every component describes itself through machine-readable metadata and parameter schemas, so an agent can search the library, inspect components, compose validated workflows, and register new ones that become discoverable in turn. Every call is validated, seeded, and traced, and sessions export as runnable notebooks, making experiments reproducible by construction. One specification layer drives the Model Context Protocol (MCP), agent-framework adapters, a Python API, a CLI, and local model serving, while data and models never leave the machine. Benchmarks show TuiML remains predictively competitive with scikit-learn and Weka. While looking like a conventional library to a human user, TuiML is designed for agents first, allowing them to read, extend, and operate machine learning autonomously. TuiML is open source, with documentation at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.17984 — 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 2026-10-15T14:08:19.224Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).