Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions

TL;DR

HCLA is a human-centered multi-agent system that enhances interpretability and accountability in digital asset transaction anomaly detection by reconstructing expert reasoning through natural language interaction and structured evidence analysis.

Contribution

The paper introduces HCLA, a novel human-centered multi-agent framework that improves transparency and decision traceability in cryptocurrency anomaly detection, emphasizing accountability over traditional explainability.

Findings

HCLA improves interpretability and transparency in anomaly detection.

The system achieves strong predictive accuracy with enhanced user interaction.

It effectively reconstructs expert reasoning aligned with regulatory standards.

Abstract

We present HCLA, a human-centered multi-agent system for anomaly detection in digital-asset transactions. The system integrates three cognitively aligned roles: Rule Abstraction, Evidence Scoring, and Expert-Style Justification. These roles operate in a conversational workflow that enables non-experts to express analytical intent in natural language, inspect structured risk evidence, and obtain traceable, context-aware reasoning. Implemented with an open-source, web-based interface, HCLA translates user intent into explicit analytical rules, applies classical anomaly detectors to quantify evidential risk, and reconstructs expert-style justifications grounded in observable transactional signals. Experiments on a cryptocurrency anomaly dataset show that, while the underlying detector achieves strong predictive accuracy, HCLA substantially improves interpretability, interaction, and decision transparency. Importantly, HCLA is not designed to explain a black-box model in the conventional XAI sense. Instead, we reconstruct a traceable expert reasoning process that aligns algorithmic evidence with regulatory and investigative judgment. By explicitly separating evidence scoring from expert-style justification, the framework emphasizes accountability beyond explainability and addresses practical requirements for regulatory, audit, and compliance-driven financial forensics. We describe the system architecture, closed-loop interaction design, datasets, evaluation protocol, and limitations. We argue that a human-in-the-loop reasoning reconstruction paradigm is essential for achieving transparency, accountability, and trust in high-stakes financial environments. Keywords: Human-Centered AI; LLM-Agent System; Multi-Agent Architecture; Anomaly Detection; Digital Asset Transactions; Cryptocurrency Forensics; Blockchain Analytics; Human-in-the-Loop; Explainable AI (XAI); Interpretability