LATIDIA · Investigación

El tipo de memoria varía: empoderar a los agentes de LLM para la memoria a largo plazo con estrategias diversas

arXiv:2610.11573v1 Anuncio Tipo: nuevo Resumen: Las capacidades de memoria de los modelos de lenguaje grandes (LLM) han atraído cada vez más atención recientemente. A pesar del gran éxito alcanzado, los enfoques de memoria basados ​​en recuperación existentes

La noticia

arXiv:2610.11573v1 Announce Type: new Abstract: The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approaches typically overlook the differences between memories and employ a unified strategy to process all memories, leading to suboptimal performance. Thus, an intuitive question arises: can we categorize memory into different types and select appropriate strategies? However, given the topic-rich, scenario-complex, and boundary-blurred nature of memory scenarios, achieving precise classification of memories is not easy. To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios. Building upon this foundation, we