LATIDIA · Investigación

BuySideFlow: un punto de referencia en el tiempo para los agentes de LLM en la investigación de inversiones

arXiv: 2611.12966v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grandes (LLM) pueden generar flujos de trabajo SQL y SQL-Python para la investigación de inversiones, pero garantizar la validez puntual (Pit) sigue siendo un desafío. Los agentes deben

La noticia

arXiv:2611.12966v1 Announce Type: new Abstract: Large language models (LLMs) can generate SQL and SQL--Python workflows for investment research, but ensuring point-in-time (PIT) validity remains challenging. Agents must enforce disclosure cutoffs and select the appropriate historical states and record versions throughout data retrieval and financial analysis. We introduce \textsc{BuySideFlow}, a benchmark of 408 practitioner-derived Chinese-language tasks spanning equities, funds, fixed income, and macroeconomics over a fixed snapshot from a licensed production financial database. We provide executable references and a taxonomy of temporal errors, pairing result checks with expert audits of executed workflows. We evaluate nine agent configurations on all tasks, with result accuracy ranging from 16.2\% to 36.8\%. An audit of