LATIDIA · Robótica
Consenso interno, competencia externa: equipos de LLM descentralizados para la defensa perimetral
arXiv:2610.41044v2 Tipo de anuncio: sustitución cruzada Resumen: El uso de modelos de lenguaje de gran tamaño (LLM) para coordinar equipos de múltiples agentes plantea una cuestión arquitectónica fundamental: si la asignación de tareas debe ser centralizada.
WhatsApp ↗Telegram ↗
La noticia
arXiv:2610.41044v2 Announce Type: replace-cross Abstract: The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a single LLM controller or distributed across autonomous LLM agents, particularly when communication is unreliable. In a deliberately simplified perimeter-defense simulation against LLM-controlled intruders, we compared a central commander, an auction-based consensus team and independent agents under five network conditions. Breach rates were 15% for the consensus team, 32% for the commander and 29% for independent agents. Burst message loss, falsified reports and limited radio range raised the commander's breach rate by 10 to 18 percentage points (pp), whereas the consensus team's