LATIDIA · Investigación

FedSkillGit: Evolución federada de habilidades a través del control de versiones

arXiv: 2610.21348v1Tipo de anuncio: nuevo Resumen: Los agentes de modelos de lenguaje grandes pueden mejorar sus capacidades mediante la evolución de habilidades de lenguaje natural reutilizables a partir de la experiencia de ejecución. En implementaciones del mundo real, esta experiencia

La noticia

arXiv:2610.21348v1 Announce Type: new Abstract: Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution. The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation. That design is poorly matched to skill evolution for three reasons. An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in