Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives

2025-09-10

AI Summary

Suspicious Activity Report (SAR) generation in anti-money laundering (AML) faces high operational costs, poor scalability, and compliance risks—including factual hallucinations, inaccurate crime-type classification, and low interpretability—when relying on large language models (LLMs). Method: We propose a multi-agent collaborative framework integrating a planning agent, a crime-type identification agent, an external intelligence retrieval agent, and a compliance verification agent. It incorporates an Agent-as-a-Judge real-time adjudication mechanism, dynamic memory management, and an AI-privacy protection layer to ensure accuracy, auditability, and data security. Results: Experiments demonstrate significant improvements in SAR generation efficiency and regulatory alignment. The framework enables human-in-the-loop review, maintains high precision, and enhances decision transparency and compliance controllability—offering a practical, deployable pathway for intelligent financial compliance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from factual hallucination, limited crime typology alignment, and poor explainability -- posing unacceptable risks in compliance-critical domains. This paper introduces Co-Investigator AI, an agentic framework optimized to produce Suspicious Activity Reports (SARs) significantly faster and with greater accuracy than traditional methods. Drawing inspiration from recent advances in autonomous agent architectures, such as the AI Co-Scientist, our approach integrates specialized agents for planning, crime type detection, external intelligence gathering, and compliance validation. The system features dynamic memory management, an AI-Privacy Guard layer for sensitive data handling, and a real-time validation agent employing the Agent-as-a-Judge paradigm to ensure continuous narrative quality assurance. Human investigators remain firmly in the loop, empowered to review and refine drafts in a collaborative workflow that blends AI efficiency with domain expertise. We demonstrate the versatility of Co-Investigator AI across a range of complex financial crime scenarios, highlighting its ability to streamline SAR drafting, align narratives with regulatory expectations, and enable compliance teams to focus on higher-order analytical work. This approach marks the beginning of a new era in compliance reporting -- bringing the transformative benefits of AI agents to the core of regulatory processes and paving the way for scalable, reliable, and transparent SAR generation.

Problem

• Generating compliant Suspicious Activity Reports with high accuracy
• Overcoming LLM limitations like hallucination and poor explainability
• Streamlining AML workflows through AI-human collaborative efficiency

Innovation

• Agentic framework for faster, accurate SAR generation
• Specialized agents for planning, detection, and validation
• Dynamic memory, privacy guard, and real-time validation