区块链上的自主代理：标准、执行模型与信任边界
Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries
AI总结：
本文系统梳理了区块链与自主代理的互操作性领域，提出了五类整合模式、定制化的威胁模型和能力矩阵，并提出了研究路线图和评估套件，旨在提升链上执行的安全性和可靠性。
摘要：
大语言模型的发展使能够推理、规划并与外部工具交互的代理式人工智能系统得以实现，以执行多步骤工作流。同时，公共区块链已演变为一种可编程的底层架构，用于价值转移、访问控制和可验证的状态转换。它们的融合引入了一个高风险的系统挑战：设计标准、互操作且安全的接口，使代理能够观察链上状态、制定交易意图并授权执行，而不会使用户、协议或组织暴露于不可接受的安全、治理或经济风险中。本文通过系统文献综述系统化地梳理了代理-区块链互操作性新兴领域，从超过3000条记录中确定了317篇相关作品。我们贡献了五类整合模式的分类，涵盖只读分析、模拟和意图生成、委托执行、自主签名以及多代理工作流；一个针对代理驱动的交易管道定制化的威胁模型，涵盖从提示注入和政策滥用到密钥泄露、对抗性执行动态以及多代理合谋等风险；以及一个比较能力矩阵，分析了超过20个代表性系统在13个维度上的能力，包括保管模型、权限控制、政策执行、可观测性以及恢复。基于此分析揭示的空白，我们提出了一个以两个接口抽象为中心的研究路线图：交易意图模式用于可移植且无歧义的目标规范，以及政策决策记录用于跨执行环境的可审计、可验证的政策执行。最后，我们提出了一套可重复使用的评估套件和基准，用于评估代理驱动的链上执行的安全性、可靠性以及经济稳健性。
英文摘要：
Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substrate for value transfer, access control, and verifiable state transitions. Their convergence introduces a high-stakes systems challenge: designing standard, interoperable, and secure interfaces that allow agents to observe on-chain state, formulate transaction intents, and authorize execution without exposing users, protocols, or organizations to unacceptable security, governance, or economic risks. This survey systematizes the emerging landscape of agent-blockchain interoperability through a systematic literature review, identifying 317 relevant works from an initial pool of over 3000 records. We contribute a five-part taxonomy of integration patterns spanning read-only analytics, simulation and intent generation, delegated execution, autonomous signing, and multi-agent workflows; a threat model tailored to agent-driven transaction pipelines that captures risks ranging from prompt injection and policy misuse to key compromise, adversarial execution dynamics, and multi-agent collusion; and a comparative capability matrix analyzing more than 20 representative systems across 13 dimensions, including custody models, permissioning, policy enforcement, observability, and recovery. Building on the gaps revealed by this analysis, we outline a research roadmap centered on two interface abstractions: a Transaction Intent Schema for portable and unambiguous goal specification, and a Policy Decision Record for auditable, verifiable policy enforcement across execution environments. We conclude by proposing a reproducible evaluation suite and benchmarks for assessing the safety, reliability, and economic robustness of agent-mediated on-chain execution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
