LATIDIA · Investigación

MemScope: Arquitecturas de memoria de agentes en evolución a través de la reparación de código localizado

arXiv: 2610.21170v1Announce Type: new Resumen: Las arquitecturas de memoria del agente definen cómo los agentes LLM almacenan y reutilizan la experiencia en todas las tareas, pero generalmente se corrigen después de la implementación, lo que limita su adaptabilidad en

La noticia

arXiv:2610.21170v1 Announce Type: new Abstract: Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across task types. Recent self-evolving approaches instead adapt these memory architectures using execution feedback, typically represented as evaluation scores or compressed summaries. However, such coarse-grained feedback is insufficient for precise failure localization in current agent systems, where long-horizon task execution involves multiple interacting components. Without a precise failure location, existing approaches lack a clear code-level target for modification, leaving the update scope weakly constrained and often leading to large-scale rewrites of an otherwise capable memory architecture. We propose MemScope, a framework for