LATIDIA · Investigación

AlphaDiverse: Agentes de investigación cuantitativa local posteriores a la capacitación para la exploración diversa en la minería de factores alfa

arXiv: 2609.29014v1Tipo de anuncio: nuevo Resumen: Los sistemas multiagente basados en el modelo de lenguaje grande (LLM) pueden automatizar la minería de factores alfa, pero su dependencia de API externas limita el control sobre el costo, la disponibilidad y la confianza

La noticia

arXiv:2609.29014v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, availability, and confidentiality. Long research loops also tend to revisit a few successful economic mechanisms that lead to research path collapse. To address these limitations, we propose AlphaDiverse, a framework that integrates a multi-agent alpha research system, diverse research path collection, and post-training for local agents. We let the research system generate complementary plan portfolios and vary research environments across loops to collect diverse research paths. Using these diverse traces, we warm-start local Planner and Realizer agents with supervised fine-tuning. Then, we propose a