LATIDIA · Investigación

LLM-as-an-Improver: Convertir la verificación en mejores candidatos

arXiv:2609.19515v1 Announce Type: new Resumen: La selección basada en verificadores mejora el rendimiento de LLM al generar múltiples soluciones candidatas y usar un verificador para seleccionar la más prometedora. Sin embargo, el método existente

La noticia

arXiv:2609.19515v1 Announce Type: new Abstract: Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. However, existing methods typically treat verification only as a ranking step and discard its feedback once a fixed candidate pool has been evaluated. In this paper, we ask whether verification can also improve the candidate set itself. To this end, we introduce LLM-as-an-Improver and propose Verify--Repair--Reselect (VRR), which uses verification feedback to generate and reselect improved candidates. VRR retains the initial winner while conditionally generating three complementary alternatives: repaired versions of the winner and runner-up, and a solution based on a new approach. It filters