LATIDIA · Investigación

TuiML: aprendizaje automático para agentes de IA

arXiv:2609.17984v1 Tipo de anuncio: nuevo Resumen: Las bibliotecas de aprendizaje automático como Weka y scikit-learn fueron diseñadas para programadores humanos. Los agentes de modelos de lenguaje ahora usan estas mismas bibliotecas recuperando API de memo

La noticia

arXiv:2609.17984v1 Announce Type: new Abstract: 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,