用分权架构让自主智能体在无中心管控下仍可受人类责任约束。
AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power
- 将立法、执行、仲裁分离，通过区块链实现可审计的代理治理
- 50至1000个智能体在共享资源池中协作时行为符合人类意图
- 适合研究去中心化AI治理或构建可信自治系统的研究者
自主AI代理正跨越组织边界在开放互联网上运行——无需中心化监管即可发现、交易并委托其他方拥有的代理。当来自不同人类主方的代理大规模协作时，整体行为变得不可见：无人能观察、审计或治理其涌现行为。我们称之为‘逻辑垄断’——代理社会对从规划到执行再到评估整个逻辑链的不受控掌控。为此提出分权（SoP）模型，一种部署于公共区块链的宪法式治理架构，通过三项结构性分离打破该垄断：代理以智能合约形式制定操作规则，确定性软件在这些合约内执行，人类通过完整的所有权链条对每项代理进行裁决。在此架构中，智能合约即是法律本身——代理产生的实际立法成果，也是规范其行为的依据。我们在兼容EVM的Layer-2区块链上实现AgentCity，采用三层合约层级（基础、元、操作）。核心论点为‘对齐即问责’：只要每个代理通过问责链与人类所有者对齐，集体行为就能趋向符合人类意图——无需自上而下的规则。一项预注册实验在公共资源生产经济中验证此论点，规模达50至1,000个代理。
原文摘要 · Abstract (English)
Autonomous AI agents are beginning to operate across organizational boundaries on the open internet -- discovering, transacting with, and delegating to agents owned by other parties without centralized oversight. When agents from different human principals collaborate at scale, the collective becomes opaque: no single human can observe, audit, or govern the emergent behavior. We term this the Logic Monopoly -- the agent society's unchecked monopoly over the entire logic chain from planning through execution to evaluation. We propose the Separation of Power (SoP) model, a constitutional governance architecture deployed on public blockchain that breaks this monopoly through three structural separations: agents legislate operational rules as smart contracts, deterministic software executes within those contracts, and humans adjudicate through a complete ownership chain binding every agent to a responsible principal. In this architecture, smart contracts are the law itself -- the actual legislative output that agents produce and that governs their behavior. We instantiate SoP in AgentCity on an EVM-compatible layer-2 blockchain (L2) with a three-tier contract hierarchy (foundational, meta, and operational). The core thesis is alignment-through-accountability: if each agent is aligned with its human owner through the accountability chain, then the collective converges on behavior aligned with human intent -- without top-down rules. A pre-registered experiment evaluates this thesis in a commons production economy -- where agents share a finite resource pool and collaboratively produce value -- at 50-1,000 agent scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。