LATIDIA · Investigación

¿Cuándo intervenir? Un estudio empírico de errores y autorrecuperación en agentes de LLM.

arXiv:2610.36471v1 Announce Type: new Resumen: Los agentes LLM interactúan con los servicios web para realizar tareas en nombre de los usuarios. Los errores durante estas interacciones pueden interrumpir la ejecución e impedir la finalización de la tarea, motivando a exte

La noticia

arXiv:2610.36471v1 Announce Type: new Abstract: LLM agents interact with Web services to perform tasks on users' behalf. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention. However, agents may self-recover through continued execution, raising the question of when to intervene and when to wait for self-recovery. We present an empirical study of errors and self-recovery in LLM agents. We construct ReInBench, a dataset containing 1,259 agent traces and 1,403 error events across computer-use and Web tasks. Our study examines how often and how quickly agents self-recover, how self-recovery relates to subsequent execution and task completion, and whether self-recovery can be predicted when an error occurs.