LATIDIA · Ciberseguridad

Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery (Descubrimiento progresivo de habilidades como control de acceso para agentes de LLM que utilizan herramientas:

arXiv: 2609.28693v1Announce Type: Cross Resumen: Los agentes del Modelo de Lenguaje Grande (LLM) tienen dificultades para escalar de forma segura cuando se exponen a vastos conjuntos de herramientas empresariales. Proporcionar a un agente acceso a todas las herramientas internas conduce a oversi

La noticia

arXiv:2609.28693v1 Announce Type: cross Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal tool leads to oversized context windows, degraded tool selection, and severe governance vulnerabilities - as system policies defined purely in prompts remain probabilistic advice rather than hard constraints. Existing mitigations, such as multi-agent domain delegation, decentralize audit logs and fail to guarantee policy compliance across sessions. We introduce skilder, a framework that packages capabilities into roles: bundles of skills, tools, and instructions, together with the limits that bound them. An agent begins with a minimal role catalog, learns the roles a task