LATIDIA · Investigación

Compensaciones entre el coste y el éxito de la arquitectura del agente: una evaluación controlada a través de los SOP de estilo empresarial

arXiv: 2611.12953v1Tipo de anuncio: nuevo Resumen: Las empresas utilizan cada vez más agentes de modelos de lenguaje grandes para ejecutar procedimientos operativos estándar (SOP): flujos de trabajo largos, ramificados e intensivos en herramientas. Sin embargo, hay poca estafa

La noticia

arXiv:2611.12953v1 Announce Type: new Abstract: Enterprises increasingly use large language model agents to execute standard operating procedures (SOPs): long, branching, tool-intensive workflows. Yet there is little controlled evidence for choosing among competing agentic architectures. Holding the model, tasks, and tools fixed and varying only the architecture, we compare four designs (a function-calling single agent, a skill-augmented agent, centralized multi-agent orchestration, and a triage swarm; eight arms) across 13 enterprise SOPs, and introduce a skill-definition quality rubric to build matched high and low-quality skill corpora. Three takeaways emerge. (1)~\textbf{There is no universal best architecture; the right choice is SOP-dependent.} On a given SOP, task success ranges from under $10\%$ on the