Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions
This work addresses the need for transparency and trust in financial forensics for non-experts, though it is incremental as it builds on existing detection methods with a focus on human-in-the-loop design.
The paper tackles the problem of detecting anomalous digital asset transactions by introducing HCLA, a human-centered multi-agent system that links parsing, detection, and explanation roles into a conversational workflow for non-experts, achieving strong accuracy on a Bitcoin mixing dataset while adding interpretability and interactive refinement.
We present HCLA, a human-centered multi-agent system for anomaly detection in digital asset transactions. The system links three roles: Parsing, Detection, and Explanation, into a conversational workflow that lets non-experts ask questions in natural language, inspect structured analytics, and obtain context-aware rationales. Implemented with an open-source web UI, HCLA translates user intents into a schema for a classical detector (XGBoost in our prototype) and returns narrative explanations grounded in the underlying features. On a labeled Bitcoin mixing dataset (Wasabi Wallet, 2020-2024), the baseline detector reaches strong accuracy, while HCLA adds interpretability and interactive refinement. We describe the architecture, interaction loop, dataset, evaluation protocol, and limitations, and discuss how a human-in-the-loop design improves transparency and trust in financial forensics.