LATIDIA · Investigación

EvolveTrade: Refinamiento de políticas basado en la experiencia para agentes de trading LLM autónomos

arXiv: 2609.17632v1Tipo de anuncio: nuevo Resumen: Los agentes de trading del modelo de lenguaje grande (LLM) pueden combinar datos de mercado, noticias y análisis ejecutables, pero su comportamiento a menudo está controlado por un pol estático de uso de herramientas escritas a mano

La noticia

arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing market regimes. We introduce EvolveTrade, a self-evolving framework that treats the system prompt of a tool-using trading agent as a text-parameterized policy. After each update interval, a Policy Agent revises this policy using accumulated decision traces and realized portfolio feedback, while keeping the backbone LLM fixed. The updated policy is then used for the next batch