LATIDIA · Robótica
ESI: Un volante de inercia de superación personal incorporado para agentes LLM-VLA
arXiv:2611.18176v1 Tipo de anuncio: nuevo Resumen: Los modelos lingüísticos preentrenados de forma independiente y las políticas de visión-lenguaje-acción (VLA) proporcionan elementos básicos complementarios para los agentes corporizados, pero conectarlos no...
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.18176v1 Announce Type: new Abstract: Independently pretrained language models and vision-language-action (VLA) policies provide complementary building blocks for embodied agents, but connecting them does not automatically produce coordinated behavior. The VLA may generate actions that diverge from the LLM's intended subtask and, upon regaining control after a correction, undo the promising state restored by the LLM. We introduce ESI (Embodied Self-Improvement), an automated flywheel that uses environmental interaction to align reasoning and action. ESI treats the modular agent as the unit of post-training, repeatedly refining the prompts that guide the LLM, the shared skill interface that expresses its intent, and the VLA parameters that realize that intent, then redeploying these