LATIDIA · Robótica

HarnessPAI: un arnés en evolución para la IA física

arXiv:2609.29166v1 Anuncio Tipo: nuevo Resumen: La IA física tiene como objetivo construir agentes encarnados que perciban el mundo, lo entiendan y razonen sobre él, y decidan cómo actuar. Sin embargo, el campo se ha centrado principalmente en las últimas

La noticia

arXiv:2609.29166v1 Announce Type: new Abstract: Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component: the action model that maps observations to low-level controls. The prevailing training recipe can erode the perceptual and reasoning capabilities needed for robust behavior, leaving even strong action models vulnerable to scene perturbations and long-horizon tasks. We introduce HarnessPAI, a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable and evolvable interface that organizes the underlying action primitive. The framework separates two timescales: within a rollout, it executes open-loop