MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions

2025-12-07

AI Summary

Ethereum’s complex transactions—such as multi-hop token flows and nested contract invocations—exhibit semantic opacity, exposing users to high risks of blind signing. To address this, we propose the first cognition-inspired multi-agent framework for transaction explainability, integrating on-chain execution traces with off-chain protocol knowledge. Our method operates through four coordinated stages: collaborative hypothesis generation, dynamic knowledge retrieval, evidence-aware textual synthesis, and adversarial validation—enabling trustworthy, incremental transaction explanations. Key contributions include: (1) introducing cognitive reasoning into multi-agent collaboration to support a semantics-driven hypothesis–validation loop; and (2) establishing an evidence-aware explanation generation paradigm that jointly optimizes accuracy and human readability. Experiments demonstrate substantial improvements in explanation completeness and user comprehension, reducing blind-signing risk by 62.3%.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Multiagent Systems: Mechanism Design
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Security and Privacy: Data transparency and provenance

Abstract

Understanding a complicated Ethereum transaction remains challenging: multi-hop token flows, nested contract calls, and opaque execution paths routinely lead users to blind signing. Based on interviews with everyday users, developers, and auditors, we identify the need for faithful, step-wise explanations grounded in both on-chain evidence and real-world protocol semantics. To meet this need, we introduce (matex, a cognitive multi-agent framework that models transaction understanding as a collaborative investigation-combining rapid hypothesis generation, dynamic off-chain knowledge retrieval, evidence-aware synthesis, and adversarial validation to produce faithful explanations.

Problem

• Explains complex Ethereum transactions with multi-hop token flows
• Addresses opaque execution paths and nested contract calls
• Provides faithful explanations using on-chain and real-world semantics

Innovation

• Multi-agent framework models transaction understanding collaboratively
• Combines hypothesis generation with dynamic off-chain knowledge retrieval
• Integrates evidence-aware synthesis and adversarial validation for explanations