LATIDIA · Investigación

Arnés de agente seguro, persistente y en evolución para comprender mundos parcialmente observables

arXiv:2610.11552v1 Anuncio Tipo: nuevo Resumen: Los agentes de modelos de lenguaje grandes pueden invocar herramientas con fluidez, pero los flujos de trabajo empresariales exigen más que seleccionar las herramientas adecuadas: las acciones deben cumplir estrictamente con las normas organizativas.

La noticia

arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking across multiple records. To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution. E-Ledger employs a code approval layer that checks every proposed action against policy before execution, and maintains a world ledger of verified hidden rules alongside evidence-backed dynamic state. Because hidden rules are typically unknown a priori, we further propose WorldAbduct, an abductive, world-model-driven harness evolution