LATIDIA · Investigación

Posición: Es hora de virtualizar los modelos básicos con una capa de sistema operativo autoevolutiva

arXiv:2609.19203v1 Announce Type: new Abstract: Las aplicaciones de IA han pasado de modelos de cimientos monolíticos únicos (FM) a sistemas agénticos compuestos. Sin embargo, las pilas actuales siguen fragmentadas: incluso cuando los protocolos (por ejemplo, MCP,

La noticia

arXiv:2609.19203v1 Announce Type: new Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime for state, memory, budgets, and guardrails, making behavior non-portable and governance brittle. It mirrors computing before operating systems, when every program re-implemented basic services. This position paper argues that the field now needs a Foundation Model Operating System (FMOS) -- a system layer that virtualizes FM interactions analogous to how virtual machines abstract physical hardware, giving applications the illusion of dedicated, trustworthy FM instances with effectively unbounded capabilities. Internally, the FMOS