VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation

TL;DR

VERAFI is a neurosymbolic framework that significantly improves the factual correctness and regulatory compliance of financial AI systems by integrating domain expertise and automated reasoning.

Contribution

It introduces VERAFI, a novel neurosymbolic agentic framework combining advanced retrieval, financial tools, and reasoning policies for verified financial intelligence.

Findings

VERAFI achieves 94.7% factual correctness on FinanceBench.

The neurosymbolic policy layer improves accuracy by 4.3 percentage points.

Traditional methods reach only 52.4% correctness.

Abstract

Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during reasoning, even with perfect retrieval. This paper introduces VERAFI (Verified Agentic Financial Intelligence), an agentic framework with neurosymbolic policy generation for verified financial intelligence. VERAFI combines state-of-the-art dense retrieval and cross-encoder reranking with financial tool-enabled agents and automated reasoning policies covering GAAP compliance, SEC requirements, and mathematical validation. Our comprehensive evaluation on FinanceBench demonstrates remarkable improvements: while traditional dense retrieval with reranking achieves only 52.4\% factual correctness, VERAFI's integrated approach reaches 94.7\%, an 81\% relative improvement. The neurosymbolic policy layer alone contributes a 4.3 percentage point gain over pure agentic processing, specifically targeting persistent mathematical and logical errors. By integrating financial domain expertise directly into the reasoning process, VERAFI offers a practical pathway toward trustworthy financial AI that meets the stringent accuracy demands of regulatory compliance, investment decisions, and risk management.