LATIDIA · Robótica

Un marco local de IA agénica para generar escenarios de casos de vanguardia para la garantía de la seguridad

arXiv: 2610.13479v1Tipo de anuncio: Cross Resumen: La generación de escenarios de casos extremos es crucial para la capacitación, las pruebas y la garantía de seguridad de los sistemas autónomos. Esto identifica fallas peligrosas para aumentar la confiabilidad del sistema

La noticia

arXiv:2610.13479v1 Announce Type: cross Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of its operational design domain and learns the expected system behaviour for these edge cases. The rapid advancement in the generation and analysis capabilities of language models (LMs) has expanded their applicability and recent work has investigated LM scenario generation. However, many recent approaches rely on human-in-the-loop or rule-based strategies. This restricts the LM's ability to generate diverse and edge case scenarios; the long tail of the distribution. Our work uses