An Agentic LLM Framework for Adverse Media Screening in AML Compliance

Researchers have developed an agentic LLM framework using Retrieval-Augmented Generation to automate adverse media screening for anti-money laundering compliance in financial institutions. The system addresses high false-positive rates in traditional keyword-based approaches by implementing multi-step web searches and computing Adverse Media Index scores to distinguish between high-risk and low-risk individuals.

• →Traditional AML adverse media screening relies on keyword searches with high false-positive rates requiring extensive manual review.
• →The new agentic system uses LLMs with RAG to automate web searches and document processing for compliance screening.
• →The framework computes an Adverse Media Index score to quantify risk levels for each screened individual.
• →Testing was conducted on datasets including Politically Exposed Persons, regulatory watchlists, and sanctioned individuals from OpenSanctions.
• →The system demonstrates ability to differentiate between high-risk and low-risk persons for KYC compliance processes.