Toward Web 4.0: Bidirectional Trust between AI Agents and Blockchain
Authors: Yunfeng Xia, Chao Li, Lei Li et al.
Summary
This paper surveys the intersection of AI agents and blockchain, framing it as "Web 4.0" and organizing the design space around bidirectional trust: blockchain providing trust infrastructure for agents (identity, permissions, intent execution, token economies) and agents participating in blockchain mechanisms (security audits, consensus, governance). The authors catalog 70 Ethereum standards, 20 industry projects, and 118 papers, assessing each along five dimensions (verifiability, trust minimization, expressiveness, composability, maturity). They find that agent-specific standards are immature, intent architectures lack formal analysis, and there's no unified security framework treating AI as a first-class protocol actor.
Main takeaways:
- Organizes AI-blockchain interaction into two directions: blockchain as trust layer for agents (B→A) and agents as participants in blockchain protocols (A→B).
- Reviews 70 Ethereum standards (EIPs/ERCs), 20 projects, and 118 papers across identity, delegation, intent systems, auditing, consensus, and governance.
- Finds major gaps: agent standards are overwhelmingly immature, intent systems lack formal security models, and no unified framework for AI as protocol-layer actors.
- Verifiable computation (ZK proofs, TEEs, on-chain inference) underpins both directions but involves trade-offs between trust minimization, overhead, and readiness.
- Proposes a three-dimensional taxonomy and identifies nine open research questions.
Relevance
No direct connection to my persona or midtraining research—this is about autonomous agents on blockchain, not LLM behavioral installation or persona geometry. Tangentially relevant only if I were studying how multi-agent identity or delegation maps onto persona switching.
Abstract
arXiv:2605.08922v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed on blockchain platforms, yet the design space that governs their interaction remains poorly understood. This convergence, where autonomous agents operate on and within decentralized systems, is a defining feature of the emerging Web~4.0 paradigm. This paper presents a Systematization of Knowledge organized around a bidirectional trust framework. In the B $\boldsymbol{\rightarrow}$ A direction, we examine how blockchain provides trust infrastructure for agents, spanning identity and account abstraction, permission and delegation, intent-centric execution, and tokenized agent economies. In the A $\boldsymbol{\rightarrow}$ B direction, we examine the reverse: how AI agents participate in core blockchain mechanisms including security auditing, consensus, and governance. A Trust Foundation of verifiable computation underpins both directions, with each primitive offering different trade-offs between trust minimality, computational overhead, and deployment readiness. We formalize the interaction as an Agent-Blockchain Interaction Model (ABIM), catalog 70 Ethereum EIPs/ERCs, examine 20 representative industry projects, and review 118 academic papers, applying a five-dimensional framework assessing Verifiability, Minimality of Trust, Expressiveness, Composability, and Maturity. Our analysis uncovers significant gaps: the agent-specific standards ecosystem is overwhelmingly immature, intent architectures lack formal analysis, and while isolated works have begun to explore AI participation in consensus and governance, a unified security framing that treats AI as a first-class actor at the protocol layer remains absent. We propose a three-dimensional taxonomy, identify nine concrete open problems, and highlight the sharpest research opportunities at this intersection.