LATIDIA · Robótica

AtomTree: Un marco jerárquico para el seguimiento de instrucciones encarnadas con conciencia del estado mediante LLM.

arXiv:2610.38744v1 Anuncio Tipo: nuevo Resumen: El seguimiento de instrucciones encarnadas en entornos interactivos requiere que los agentes interpreten comandos en lenguaje natural y completen tareas de largo plazo. Los planificadores existentes

La noticia

arXiv:2610.38744v1 Announce Type: new Abstract: Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further