LATIDIA · Investigación

Recuperación de gráficos guiada por activación para la reconstrucción de la memoria cognitiva en sistemas de modelos de lenguaje

arXiv: 2611.13127v1Announce Type: new Resumen: Los sistemas de modelos de lenguaje aumentados por recuperación generalmente seleccionan el contexto por relevancia condicionada por consulta. Argumentamos que los sistemas de IA de larga vida requieren un segundo operador: activatio

La noticia

arXiv:2611.13127v1 Announce Type: new Abstract: Retrieval-augmented language model systems generally select context by query-conditioned relevance. We argue that long-lived AI systems require a second operator: activation-conditioned memory availability. We specify an architecture in which request and goal cues seed an authorized memory graph, activation and fan attenuation allocate a bounded traversal frontier, retrieved entities recursively emit cues, and a typed evidence graph is reconstructed before generation. The specification yields five architectural consequences about candidate selection, traversal control, graph regularization, evidence reconstruction, and reinforcement. We derive implementation-level cost estimates and define ablations, failure conditions, and a reproducible evaluation protocol. The central claim is narrowed or falsified if a simpler graph reranker