MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions
This addresses the problem of opaque transaction understanding for Ethereum users, developers, and auditors, offering a domain-specific solution.
The paper tackles the challenge of understanding complex Ethereum transactions by introducing MATEX, a multi-agent framework that generates step-wise explanations using on-chain evidence and real-world semantics, resulting in a system that produces faithful explanations through collaborative investigation.
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.