LATIDIA · Robótica

Orquestación LLM persistente de equipos de robots heterogéneos a través de la delegación parcial a protocolos multiagente

arXiv: 2610.15224v1Announce Type: cross Abstract: Las especificaciones del lenguaje natural permiten a los usuarios no expertos trabajar en equipos de robots, y los modelos de lenguaje grandes (LLM) han demostrado recientemente su eficacia para fundamentar dicha información semántica específica

La noticia

arXiv:2610.15224v1 Announce Type: cross Abstract: Natural language specifications let non-expert users task robot teams, and large language models (LLMs) have recently proven effective at grounding such semantic specifications into plans for heterogeneous teams. Existing approaches assume missions that terminate and environments that, while unknown, do not change, but both assumptions fail in many emerging applications. For example, a disaster-response mission does not terminate, and its environment changes continuously as hazards spread and evacuees move. We identify three ways an LLM orchestrator breaks in this setting: its prompt grows without bound, its reasoning degrades as agents and targets accumulate, and it stops actively monitoring after covering the search space once. We