LATIDIA · Robótica

Rechazar el daño, completar la tarea a través de la planificación de gráficos de reglas para robots habilitados para LLM

arXiv:2610.24603v1 Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grandes (LLM) se utilizan cada vez más en la IA incorporada para la manipulación y planificación robóticas, pero su implementación en sistemas físicos expone vulnerabilidades su

La noticia

arXiv:2610.24603v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used in embodied AI for robotic manipulation and planning, but their deployment in physical systems exposes vulnerabilities such as jailbreak attacks that induce unsafe behavior. Existing inference-time defenses are mainly evaluated on short instructions containing a single hazard, whereas realistic tasks may interleave safe and unsafe sub-tasks, conceal hazardous steps, or combine individually safe actions into unsafe outcomes. Such compound instructions make it harder for a single safety decision to distinguish hazardous sub-tasks from legitimate ones, risking either overlooking the hazard or rejecting the whole instruction. We introduce safe task completion, a task that requires an LLM-enabled robot to