LATIDIA · Investigación

AutoOnboarder: Incorporación autónoma de agentes LLM

arXiv:2610.21218v1 Tipo de anuncio: nuevo Resumen: Se ha documentado que los modelos genéticos de lenguaje grande pierden la capacidad de razonamiento cuando se colocan dentro de un arnés, el software que media sus observaciones y acciones. Para

La noticia

arXiv:2610.21218v1 Announce Type: new Abstract: Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observations and actions. To reconcile these losses, we introduce AutoOnboarder, an autonomous system that adapts an agent to a task the way a trainer onboards a new employee. It places the agent under the supervision of an intelligent ``Onboarder'' coding agent, which iteratively tailors its foundation model, prompt, and harness source code to simultaneously improve performance and decrease cost. Like a real onboarding process, the Onboarder is only given tens of examples, and all evaluation data is isolated on a separate virtual machine to