CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
cs.CR, cs.AI, cs.LG
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 9 pages, 2 figures. Currently under review
Code: https://github.com/LuoXishuang0712/CryptoFlowBench
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Review on Cryptocurrency Transaction Methods for Money Laundering
- Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection
- Large Language Models for Blockchain Security: A Systematic Literature Review
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
- Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts
- ART: Automatic multi-step reasoning and tool-use for large language models
- Probing the Mystery of Cryptocurrency Theft: An Investigation into Methods for Taint Analysis
- Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
- LLM-SmartAudit: Advanced Smart Contract Vulnerability Detection
- ReAct: Synergizing Reasoning and Acting in Language Models
- GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
- AgentEvolver: Towards Efficient Self-Evolving Agent System
- Partitioning Message Passing for Graph Fraud Detection
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs