LATIDIA · Robótica

Inspeccionar robots: evaluación de las capacidades y la seguridad de la IA incorporada

arXiv:2610.06306v1 Anuncio Tipo: nuevo Resumen: Los modelos de lenguaje de propósito general son cada vez más capaces de controlar hardware robótico. Por lo tanto, comprender las capacidades y la seguridad de estos modelos cuando se implementan es cada vez más importante.

La noticia

arXiv:2610.06306v1 Announce Type: new Abstract: General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodied is therefore increasingly important for understanding their societal impact and risks. To this end, we introduce Inspect Robots, a modular, open-source framework for developing and running evaluations of embodied agents. Inspect Robots pairs customizable, reusable abstractions for specifying physical evaluations and analyzing their results with infrastructure that automates evaluation setup, execution and termination. We demonstrate Inspect Robots by using it to evaluate the capabilities and safety of six policies based on frontier language models. Inspect Robots has seen significant early uptake, receiving nearly 100,000