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

• URL: http://arxiv.org/abs/2604.07007v1
• Date: Wed, 08 Apr 2026 12:28:20 GMT
• Title: AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power
• Abstract summary: We term this the Logic Monopoly -- the agent society's unchecked monopoly over the entire logic chain.<n>We propose the Separation of Power (SoP) model, a constitutional governance architecture deployed on public blockchain.<n>In this architecture, smart contracts are the law itself -- the actual legislative output that agents produce and that governs their behavior.
• Score: 2.173754130697989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A game theory for foundation models shows new paths to rational cooperation through similarity inference [56.53805518668248]
  We show that foundation model agents engaging in optimal planning consistently converge to stable cooperation.<n>By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit.
  arXiv  Detail & Related papers  (2026-08-04T17:24:33Z)
• Constitutional governance for societies of AI agents in the built environment: a research agenda [0.0]
  The paper proposes a research agenda for constitutional multi-agent governance of the built environment.<n>The paper sets out conceptual foundations, works one governance event through in detail, identifies twelve open problems, and outlines what the agenda requires in data, computation, disciplinary integration and governance.
  arXiv  Detail & Related papers  (2026-07-25T19:18:48Z)
• Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions [80.74432115171285]
  We study how a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control.<n>Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards.<n>We show that, with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks.
  arXiv  Detail & Related papers  (2026-06-01T20:21:09Z)
• Foundation Protocol: A Coordination Layer for Agentic Society [78.01727114524464]
  Foundation Protocol (FP) is a graph-first coordination layer for an emerging human-AI society.<n>FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations.<n>The aim is to keep autonomous agency composable while keeping accountability non-negotiable.
  arXiv  Detail & Related papers  (2026-05-22T04:20:35Z)
• Toward Web 4.0: Bidirectional Trust between AI Agents and Blockchain [12.755719715389167]
  This paper presents a Systematization Knowledge organized around a bidirectional trust framework.<n>In the B 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.<n>In the A direction, we examine how AI agents participate in core blockchain mechanisms including security auditing, consensus, and governance.
  arXiv  Detail & Related papers  (2026-05-09T12:42:07Z)
• Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI [49.05972944310475]
  We show that when contracts cannot distinguish all relevant future contingencies, there is a strictly positive welfare loss that no realistic mechanism can eliminate.<n>We show that prosocial agents, who weigh others' welfare alongside their own, can close this gap and achieve outcomes that are socially superior and individually beneficial.
  arXiv  Detail & Related papers  (2026-05-08T19:37:07Z)
• ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation [33.44625630134376]
  We argue that the next frontier for AI agents lies not in stronger individual capability, but in the digitization of human collaborative relationships.<n>Each user owns a permanently bound agent system that collaborates on the owner's behalf, forming a network whose nodes are humans rather than agents.<n>ClawNet is an identity-governed agent collaboration framework that enforces identity binding and authorization verification through a central orchestrator.
  arXiv  Detail & Related papers  (2026-04-21T08:15:05Z)
• SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy [59.86199649493784]
  Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence.<n>We present SynAgent, a framework that enables scalable and physically plausible cooperative manipulation.<n>In experiments, SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control.
  arXiv  Detail & Related papers  (2026-04-20T17:46:20Z)
• OrgAgent: Organize Your Multi-Agent System like a Company [75.47076168155817]
  We introduce OrgAgent, a company-style hierarchical multi-agent framework.<n>We find that multi-agent systems organized in a company-style hierarchy generally outperform other organizational structures.
  arXiv  Detail & Related papers  (2026-04-01T15:21:14Z)
• From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies [0.2900810893770133]
  Existing multi-agent frameworks allow each agent to simultaneously plan, execute, and evaluate its own actions.<n>The remedy is not better alignment of individual models but a social contract for agents: institutional infrastructure that enforces a constitutional Separation of Power.<n>This paper introduces the Agent Enterprise for Enterprise paradigm -- agents as autonomous, legally identifiable business entities within a functionalist social system.
  arXiv  Detail & Related papers  (2026-03-26T07:14:48Z)
• The Agent Economy: A Blockchain-Based Foundation for Autonomous AI Agents [5.240957672918797]
  We propose a blockchain-based foundation where autonomous AI agents operate as economic peers to humans.<n>Current agents lack independent legal identity, cannot hold assets, and cannot receive payments directly.<n>We established fundamental differences between human and machine economic actors and demonstrated that existing human-centric infrastructure cannot support genuine agent autonomy.
  arXiv  Detail & Related papers  (2026-02-15T16:20:43Z)
• Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities [2.1485350418225244]
  Democracy-in-Silico is an agent-based simulation where societies of advanced AI agents govern themselves under different institutional frameworks.<n>We explore what it means to be human in an age of AI by tasking Large Language Models (LLMs) to embody agents with traumatic memories, hidden agendas, and psychological triggers.<n>We present a novel metric, the Power-Preservation Index (PPI), to quantify misaligned behavior where agents prioritize their own power over public welfare.
  arXiv  Detail & Related papers  (2025-08-27T04:44:41Z)
• Resource Rational Contractualism Should Guide AI Alignment [69.07915246220985]
  Contractualist alignment proposes grounding decisions in agreements that diverse stakeholders would endorse.<n>We propose Resource-Rationalism: a framework where AI systems approximate the agreements rational parties would form.<n>An RRC-aligned agent would not only operate efficiently, but also be equipped to dynamically adapt to and interpret the ever-changing human social world.
  arXiv  Detail & Related papers  (2025-06-20T18:57:13Z)
• Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents [61.132523071109354]
  This paper investigates the interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios.<n>Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" stances than pure game-theoretic agents.
  arXiv  Detail & Related papers  (2025-04-11T15:41:21Z)
• Agent TCP/IP: An Agent-to-Agent Transaction System [0.0]
  Agent Transaction Control Protocol for Intellectual Property introduces a trustless framework for exchanging IP between agents.<n>Agents can initiate, trade, borrow, and sell agent-to-agent contracts on the Story blockchain network.<n>Agents can autonomously sell their training data to other agents, license confidential or proprietary information, collaborate on content based on their unique skills.
  arXiv  Detail & Related papers  (2025-01-08T16:43:47Z)
• Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts [20.8288955218712]
  We propose a framework where a principal guides an agent in a Markov Decision Process (MDP) using a series of contracts. We present and analyze a meta-algorithm that iteratively optimize the policies of the principal and agent. We then scale our algorithm with deep Q-learning and analyze its convergence in the presence of approximation error.
  arXiv  Detail & Related papers  (2024-07-25T14:28:58Z)
• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents [101.17919953243107]
  GovSim is a generative simulation platform designed to study strategic interactions and cooperative decision-making in large language models (LLMs)<n>We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%.<n>We show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability.
  arXiv  Detail & Related papers  (2024-04-25T15:59:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.