SoK: Blockchain Agent-to-Agent Payments

Paper: arXiv 2604.03733

Authors: Yuanzhe Zhang, Yuexin Xiang, Yuchen Lei, Qin Wang, Tian Qiu, Yujing Sun, Spiridon Zarkov, Tsz Hon Yuen, Andreas Deppeler, Jiangshan Yu, Kwok-Yan Lam

Abstract

Agentic AI rivals human capabilities across a wide range of domains. Looking ahead, it is foreseeable that AI agents will autonomously handle complex workflows and interactions. Early prototypes of this paradigm are emerging, e.g., OpenClaw and Moltbook, signaling a shift toward Agent-to-Agent (A2A) ecosystems. However, despite these promising blueprints, critical trust and security challenges remain, particularly in scenarios involving financial transactions. Ensuring secure and reliable payment mechanisms between unknown and untrusted agents is crucial to complete a fully functional and trustworthy A2A ecosystem. Although blockchain-based infrastructures provide a natural foundation for this setting, via programmable settlement, transparent accounting, and open interoperability, trust and security challenges have not yet been fully addressed. Hence, for the first time, we systematize blockchain-based A2A payments, e.g., X402, with a four-stage lifecycle: discovery, authorization, execution, and accounting. We categorize representative designs at each stage and identify key challenges, including weak intent binding, misuse under valid authorization, payment-service decoupling, and limited accountability. We highlight future directions for strengthening cross-stage consistency, enabling behavior-aware control, and supporting compositional payment workflows across agents and systems.

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 3.0/10
• Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: This Systematization of Knowledge (SoK) paper introduces a timely framework for blockchain-based Agent-to-Agent (A2A) payments, categorizing the multi-stage lifecycle and identifying key security challenges. While it excels in conceptual clarity and novel structuring of an emerging paradigm, it lacks mathematical derivations, quantitative modeling, or empirical backtesting.

Research Flowchart

  flowchart TD
    A[Research Goal: Systematize Blockchain-Based<br>Agent-to-Agent Payments & Security] --> B[Data Inputs: Emerging A2A Systems<br>e.g., OpenClaw, Moltbook, X402]
    B --> C[Methodology: Systematization of Knowledge<br>Categorizing 4-Stage Payment Lifecycle]
    C --> D[Analysis: Evaluate Discovery, Authorization,<br>Execution, & Accounting Stages]
    D --> E[Key Findings: Critical Vulnerabilities<br>Weak Intent Binding, Misuse, & Payment Decoupling]
    E --> F[Outcomes: Proposed Future Directions<br>Behavior-Aware Control & Cross-Stage Consistency]

Cited References (168)

1. On the planning abilities of large language models-a critical investigation (2023)
2. Large language model based multi-agents: A survey of progress and challenges (2024) — link
3. Agentgen: Enhancing planning abilities for large language model based agent via environment and task generation (2025)
4. Agentic commerce and payments: Exploring the implications of robots paying robots (2025)
5. Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries (2026) — link
6. AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents (2025)
7. OpenClaw
8. EIP-8004: Agent Reputation and Trust Framework (2025)

1 of 168 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.