LATIDIA · Investigación

SkillNEO: Optimización evolutiva no elitista de las habilidades de los agentes

arXiv: 2610.20926v1 Tipo de anuncio: nuevo Resumen: Las habilidades de los agentes convierten el conocimiento de los procedimientos en artefactos reutilizables, lo que permite a los agentes de LLM acumular y refinar la experiencia a través de la experiencia. A partir de esto, la evolución de las habilidades

La noticia

arXiv:2610.20926v1 Announce Type: new Abstract: Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can still be worth developing. Requiring immediate reward gains can discard useful partial repairs before their benefits emerge. Non-elitist evolution allows new versions to receive further edits despite scoring below earlier ones. For agent skills, this calls for evidence of what to preserve and repair next. We introduce SkillNEO (Non-Elitist Evolutionary Optimization for Agent Skills), which separately selects a version to use and versions to keep