LATIDIA · Robótica

ORDEN: un punto de referencia del mundo ficticio para la IA incorporada adaptativa al dominio

arXiv: 2609.22285v1Tipo de anuncio: nuevo Resumen: La adaptación de los modelos de lenguaje a nuevos dominios a través de la capacitación previa continua plantea un problema básico de evaluación: si el corpus de capacitación se superpone con lo que el modelo ya sabe, por

La noticia

arXiv:2609.22285v1 Announce Type: new Abstract: Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the model already knows, performance gains cannot be cleanly attributed to new learning rather than pre-existing knowledge. This matters most for knowledge-intensive, task-light (KHTL) robot deployments - pharmaceutical dispensing, hazardous-material handling, facility-specific protocols, where the physical task is simple but the governing rules are proprietary and safety-critical, and where extensive live testing is costly or unsafe. We introduce ORDER (Ontology-driven Decision-making for Embodied Reasoning), a benchmark built on a fictitious world: a 342,069-token synthetic corpus defining a self-consistent physics that cannot appear in any