Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
- URL: http://arxiv.org/abs/2508.19562v1
- Date: Wed, 27 Aug 2025 04:44:41 GMT
- Title: Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
- Authors: Trisanth Srinivasan, Santosh Patapati,
- Abstract summary: 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.
- Score: 2.1485350418225244
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under different institutional frameworks. 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. These agents engage in deliberation, legislation, and elections under various stressors, such as budget crises and resource scarcity. We present a novel metric, the Power-Preservation Index (PPI), to quantify misaligned behavior where agents prioritize their own power over public welfare. Our findings demonstrate that institutional design, specifically the combination of a Constitutional AI (CAI) charter and a mediated deliberation protocol, serves as a potent alignment mechanism. These structures significantly reduce corrupt power-seeking behavior, improve policy stability, and enhance citizen welfare compared to less constrained democratic models. The simulation reveals that an institutional design may offer a framework for aligning the complex, emergent behaviors of future artificial agent societies, forcing us to reconsider what human rituals and responsibilities are essential in an age of shared authorship with non-human entities.
Related papers
- The Digital Gorilla: Rebalancing Power in the Age of AI [0.0]
Article offers a conceptual foundation for AI governance by treating such systems as a fourth societal actor.<n>It develops a Four Societal Actors framework that maps how power flows among these actors across five power modalities.<n>It advances a federalized, polycentric governance architecture and institutionalizes dynamic checks and balances.
arXiv Detail & Related papers (2026-02-23T17:46:54Z) - Operational Agency: A Permeable Legal Fiction for Tracing Culpability in AI Systems [0.31061678033205636]
This Article introduces Operational Agency (OA)-a permeable legal fiction structured as an ex post evidentiary framework-and Operational Agency Graph (OAG)<n>OA evaluates an AI's observable operational characteristics.<n>OAG operationalizes that analysis by embedding these characteristics in a causal graph to trace and apportion culpability among developers, fine-tuners, deployers, and users.
arXiv Detail & Related papers (2026-02-20T01:49:03Z) - LIMI: Less is More for Agency [49.63355240818081]
LIMI (Less Is More for Intelligent Agency) demonstrates that agency follows radically different development principles.<n>We show that sophisticated agentic intelligence can emerge from minimal but strategically curated demonstrations of autonomous behavior.<n>Our findings establish the Agency Efficiency Principle: machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.
arXiv Detail & Related papers (2025-09-22T10:59:32Z) - A Moral Agency Framework for Legitimate Integration of AI in Bureaucracies [0.0]
Public-sector bureaucracies seek to reap the benefits of artificial intelligence (AI)<n>We present a three-point Moral Agency Framework for legitimate integration of AI in bureaucratic structures.
arXiv Detail & Related papers (2025-08-11T17:49:19Z) - When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems [78.04679174291329]
We introduce a proof-of-concept to simulate the risks of malicious multi-agent systems (MAS)<n>We apply this framework to two high-risk fields: misinformation spread and e-commerce fraud.<n>Our findings show that decentralized systems are more effective at carrying out malicious actions than centralized ones.
arXiv Detail & Related papers (2025-07-19T15:17:30Z) - Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
arXiv Detail & Related papers (2025-06-01T07:52:16Z) - Artificial Intelligence in Government: Why People Feel They Lose Control [44.99833362998488]
The use of Artificial Intelligence in public administration is expanding rapidly.<n>While AI promises greater efficiency and responsiveness, its integration into government functions raises concerns about fairness, transparency, and accountability.<n>This article applies principal-agent theory to AI adoption as a special case of delegation.
arXiv Detail & Related papers (2025-05-02T07:46:41Z) - 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) - Media and responsible AI governance: a game-theoretic and LLM analysis [61.132523071109354]
This paper investigates the interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems.<n>Using evolutionary game theory and large language models (LLMs), we model the strategic interactions among these actors under different regulatory regimes.
arXiv Detail & Related papers (2025-03-12T21:39:38Z) - AGI, Governments, and Free Societies [0.0]
We argue that AGI poses distinct risks of pushing societies toward either a 'despotic Leviathan' or an 'absent Leviathan'<n>We analyze how these dynamics could unfold through three key channels.<n> Enhanced state capacity through AGI could enable unprecedented surveillance and control, potentially entrenching authoritarian practices.<n>Conversely, rapid diffusion of AGI capabilities to non-state actors could undermine state legitimacy and governability.
arXiv Detail & Related papers (2025-02-14T03:55:38Z) - ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in
Multi-Agent Simulations [110.72725220033983]
Epsilon-Robust Multi-Agent Simulation (ERMAS) is a framework for learning AI policies that are robust to such multiagent sim-to-real gaps.
ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations.
In particular, ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations.
arXiv Detail & Related papers (2021-06-10T04:32:20Z)
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.