IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2512.14744.html

VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation

Author

Listed:
  • Adewale Akinfaderin
  • Shreyas Subramanian

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.

Suggested Citation

  • Adewale Akinfaderin & Shreyas Subramanian, 2025. "VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation," Papers 2512.14744, arXiv.org.
    • Handle: RePEc:arx:papers:2512.14744
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2512.14744
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jingru Wang & Wen Ding & Xiaotong Zhu, 2025. "Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG," Papers 2504.06279, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Duane, Jackson & Morgan, Ashley & Carter, Emily, 2025. "A Review of Financial Data Analysis Techniques for Unstructured Data in the Deep Learning Era: Methods, Challenges, and Applications," OSF Preprints gdvbj_v1, Center for Open Science.
    2. Reams, Trent S. & Carter, Alex, 2025. "Smarter Investing for Everyone: How AI is Changing Financial Advice in Growing Economies," OSF Preprints 6zqmp_v1, Center for Open Science.
    3. Green, Alicia, 2025. "AI-Driven Financial Intelligence Systems: A New Era of Risk Detection and Strategic Analysis," OSF Preprints ynph2_v1, Center for Open Science.
    4. Duane, Jackson & Ren, Alicia & Zhang, Wei, 2025. "Deep Learning Models for Financial Data Analysis: A Focused Review of Recent Advances," OSF Preprints ctxf9_v1, Center for Open Science.
    5. Mori, Misato, 2025. "How AI Detects Financial Fraud: A Review of Emerging Deep Learning Methods," OSF Preprints 5yjm4_v1, Center for Open Science.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2512.14744. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.