LATIDIA · Robótica

¿Qué deben recordar los agentes incorporados? Evaluación comparativa y evaluación de la modalidad de memoria para agentes incorporados

arXiv: 2610.12561v1Announce Type: new Resumen: La memoria permite a los agentes del modelo de lenguaje grande (LLM) utilizar la experiencia pasada, a menudo almacenada como registros textuales, al responder a las solicitudes. Para agentes encarnados que controlan el robot

La noticia

arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 tasks across four simulated