mlsanityData to 14 Oct 2026

Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model

arXiv 2411.17724 ↗First posted 21 Nov 2024cs.MAcited by 2

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

It has been shown that social institutions impact human motivations to produce different behaviours, such as amount of working or specialisation in labor. With advancement in artificial intelligence (AI), specifically large language models (LLMs), now it is possible to perform in-silico simulations to test various hypotheses around this topic. Here, I simulate two somewhat similar worlds using multi-agent reinforcement learning (MARL) framework of the AI-Economist and generative agent-based model (GABM) framework of the Concordia. In the extended versions of the AI-Economist and Concordia, the agents are able to build houses, trade houses, and trade house building skill. Moreover, along the individualistic-collectivists axis, there are a set of three governing systems: Full-Libertarian, Semi-Libertarian/Utilitarian, and Full-Utilitarian. Additionally, in the extended AI-Economist, the Semi-Libertarian/Utilitarian system is further divided to a set of three governing institutions along the discriminative axis: Inclusive, Arbitrary, and Extractive. Building on these, I am able to show that among governing systems and institutions of the extended AI-Economist, under the Semi-Libertarian/Utilitarian and Inclusive government, the ratios of building houses to trading houses and trading house building skill are higher than the rest. Furthermore, I am able to show that in the extended Concordia when the central government care about equality in the society, the Full-Utilitarian system generates agents building more houses and trading more house building skill. In contrast, these economic activities are higher under the Full-Libertarian system when the central government cares about productivity in the society. Overall, the focus of this paper is to compare and contrast two advanced techniques of AI, MARL and GABM, to simulate a similar social phenomena with limitations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 29 of its 76 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

29 of 76 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents25 Apr
  2. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia6 Dec

Other references · 27

  1. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  2. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 107
  3. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  4. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  5. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 80
  6. 2024Building Machines that Learn and Think with Peoplecited by 73
  7. 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 69
  8. 2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 61
  9. 2021People construct simplified mental representations to plancited by 47
  10. 2024A new sociology of humans and machinescited by 32
  11. 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learningcited by 31
  12. 2018Evolving intrinsic motivations for altruistic behaviorcited by 30
15 more
  1. 2020Bridging Machine Learning and Mechanism Design towards Algorithmic Fairnesscited by 30
  2. 2023A Review of Cooperation in Multi-agent Learningcited by 29
  3. 2019Learning Reciprocity in Complex Sequential Social Dilemmascited by 24
  4. 2021A learning agent that acquires social norms from public sanctions in decentralized multi-agent settingscited by 24
  5. 2021Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economistcited by 23
  6. 2022AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-Ncited by 22
  7. 2022Emergent Bartering Behaviour in Multi-Agent Reinforcement Learningcited by 19
  8. 2024LLM Theory of Mind and Alignment: Opportunities and Riskscited by 18
  9. 2020Model-free conventions in multi-agent reinforcement learning with heterogeneous preferencescited by 13
  10. 2021Delegation to autonomous agents promotes cooperation in collective-risk dilemmascited by 3
  11. 2022Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principalcited by 2
  12. 2023Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivitycited by 2
  13. 2021Learning to Play General-Sum Games Against Multiple Boundedly Rational Agentscited by 1
  14. 2023A Multi-agent Reinforcement Learning Study of Emergence of Social Classes out of Arbitrary Governance: The Role of Environmentcited by 1
  15. 2024A Multi-agent Reinforcement Learning Study of Evolution of Communication and Teaching under Libertarian and Utilitarian Governing Systemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulationscited by 2
  2. 2026From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Artificial Institutions: How Institutional Design Shapes LLM Simulations
  2. 2025LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
  3. 2025Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics
  4. 2026Interactive Alignment ↗
  5. 2025Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach
  6. 2024Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
  7. 2026Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
  8. 2025LLMs Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents