LOCARD: An Agentic Framework for Blockchain Forensics
This work addresses the need for dynamic and iterative investigations in blockchain forensics, offering a novel approach for forensic analysts to trace complex cross-chain transactions, though it is incremental in applying agentic methods to this specific domain.
The paper tackles the problem of blockchain forensics by proposing a paradigm shift to Agentic Blockchain Forensics (ABF), modeling it as a sequential decision-making process, and introduces LOCARD, an agentic framework that achieves high-fidelity tracing results in cross-chain transaction tracing, validated on real-world data from the Bybit hack.
Blockchain forensics inherently involves dynamic and iterative investigations, while many existing approaches primarily model it through static inference pipelines. We propose a paradigm shift towards Agentic Blockchain Forensics (ABF), modeling forensic investigation as a sequential decision-making process. To instantiate this paradigm, we introduce LOCARD, the first agentic framework for blockchain forensics. LOCARD operationalizes this perspective through a Tri-Core Cognitive Architecture that decouples strategic planning, operational execution, and evaluative validation. Unlike generic LLM-based agents, it incorporates a Structured Belief State mechanism to enforce forensic rigor and guide exploration under explicit state constraints. To demonstrate the efficacy of the ABF paradigm, we apply LOCARD to the inherently complex domain of cross-chain transaction tracing. We introduce Thor25, a benchmark dataset comprising over 151k real-world cross-chain forensic records, and evaluate LOCARD on the Group-Transfer Tracing task for dismantling Sybil clusters. Validated against representative laundering sub-flows from the Bybit hack, LOCARD achieves high-fidelity tracing results, providing empirical evidence that modeling blockchain forensics as an autonomous agentic task is both viable and effective. These results establish a concrete foundation for future agentic approaches to large-scale blockchain forensic analysis. Code and dataset are publicly available at https://github.com/xhyumiracle/locard and https://github.com/xhyumiracle/thorchain-crosschain-data.