LATIDIA · Robótica

Coordinación Multi-LLM mediada por un verificador para la planificación de rutas de múltiples robots

arXiv: 2610.12761v1Tipo de anuncio: nuevo Resumen: Los modelos de cimentación se utilizan cada vez más para la planificación de tareas multirobot de alto nivel, pero los planes simbólicos generados de forma independiente pueden volverse inviables conjuntamente después de la geometría

La noticia

arXiv:2610.12761v1 Announce Type: new Abstract: Foundation models are increasingly used for high-level multi-robot task planning, yet independently generated symbolic plans can become jointly infeasible after geometric grounding because of shared spatial and temporal constraints. We study execution-aware coordination of large-language-model (LLM) planners for multi-robot navigation. We compare a centralized architecture, in which one LLM jointly reasons over the robot team, with a decentralized multi-LLM architecture in which each robot independently proposes a task plan. A geometric verifier grounds the candidate plans into robot trajectories, detects predicted inter-robot conflicts, and converts conflict information into structured feedback for targeted replanning. This verifier-mediated architecture separates semantic task reasoning from execution-level feasibility while enabling