AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power

TL;DR

AgentCity introduces a blockchain-based governance architecture that decentralizes control of autonomous agents, ensuring accountability and alignment with human intent in open multi-agent economies.

Contribution

This work presents the Separation of Power model, a novel constitutional governance framework deploying structural separations on blockchain to regulate autonomous agent societies.

Findings

Successfully instantiated SoP in AgentCity on a Layer-2 blockchain.

Demonstrated alignment of agent behavior with human owners in a shared resource economy.

Evaluated system performance at scales of 50 to 1,000 agents.

Abstract

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.