LATIDIA · Ciberseguridad

Verificación de tiempo de ejecución de múltiples aspectos para V&V basado en simulación de agentes autónomos habilitados para LLM

arXiv: 2610.08928v1Tipo de anuncio: nuevo Resumen: los agentes basados en LLM están ingresando a roles de apoyo a la decisión en el trabajo del personal de defensa, donde las obligaciones que deben respetar ya están escritas y son vinculantes, y donde el reentrenamiento

La noticia

arXiv:2610.08928v1 Announce Type: new Abstract: LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retraining is not available as a control because models arrive as procured components. What can be placed under engineering control is the interface between the agent and the systems it acts on. Those obligations are at once spatial, temporal and text-semantic, and a violation typically lives in the composition of a multi-step interaction, which is why per-event guardrails miss sequential tool-attack chains. We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one