LATIDIA · Ciberseguridad

AutoControl Arena: Sintetización de entornos de prueba ejecutables para la evaluación de riesgos de IA en la frontera

arXiv: 2603.07427v3Tipo de Anuncio: replace-cross Resumen: A medida que los Modelos de Lenguaje Grande (LLM) evolucionan hacia agentes autónomos, las evaluaciones de seguridad existentes se enfrentan a una compensación fundamental: los puntos de referencia manuales son costosos, mientras que los LLM-b

La noticia

arXiv:2603.07427v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AutoControl Arena, an automated framework for frontier AI risk evaluation built on the principle of logic-narrative decoupling. By grounding deterministic state in executable code while delegating generative dynamics to LLMs, we mitigate hallucination while maintaining flexibility. This principle, instantiated through a three-agent framework, achieves over 98% end-to-end success and 60% human preference over existing simulators. To elicit latent risks, we vary environmental Stress and Temptation across X-Bench (70 scenarios, 7 risk categories). Evaluating