mlsanityData to 14 Oct 2026

Evaluating Collective Behaviour of Hundreds of LLM Agents

arXiv 2602.16662 ↗First posted 18 Feb 2026cs.MAcited by 8

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

Abstract (arXiv)

LLM-powered AI assistants acting on behalf of users can produce poor collective outcomes at scale. We introduce a framework for evaluating their emergent behaviour in social dilemmas, applied to three iterated games (Public Goods, Collective Risk, Common Pool Resource). We prompt each model to produce a natural-language strategy, then have the same model translate it into code. This aims to isolate strategic reasoning from input-parsing, enables pre-deployment inspection, and scales to populations of hundreds of agents. We propose three analyses: behavioural fingerprinting via exhaustive evaluation over opponent histories; self-play robustness across mixtures of a model's strategies with either a Selfish or Collective disposition; and cultural evolution under payoff-biased imitation. Applied to three state-of-the-art LLMs, we find substantial cross-model differences in self-play welfare, and that cultural evolution converges to low-welfare, Selfish-dominant equilibria in larger groups.

Key facts. Cited by 8 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 22 of its 43 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

22 of 43 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma27 Jan
  2. 2024Cultural Evolution of Cooperation among LLM Agents13 Dec
  3. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents25 Apr
  4. 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents19 Feb

Other references · 18

  1. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  3. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  4. 2023Playing repeated games with Large Language Modelscited by 217
  5. 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 199
  6. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  7. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
  8. 2025Multi-Agent Risks from Advanced AIcited by 163
  9. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Modelscited by 99
  10. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 92
  11. 2023Strategic Reasoning with Language Modelscited by 64
  12. 2024Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?cited by 63
6 more
  1. 2023Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framingcited by 51
  2. 2023A Review of Cooperation in Multi-agent Learningcited by 29
  3. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  4. 2025Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Gamescited by 20
  5. 2025When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmascited by 15
  6. 2025Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"cited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026AlphaEval: Evaluating Agents in Productioncited by 1
  2. 2026Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agentscited by 1
  3. 2026Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extensioncited by 0
  4. 2026Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Gamecited by 0
  5. 2026How a shared state is described determines whether AI agents synchronizecited by 0
  6. 2026WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societiescited by 0
  7. 2026From Certain Doom to Survival: Agent-Driven Self-Governance in LLM Agent Societiescited by 0
  8. 2026Disentangling Models from Personas in Heterogeneous LLM Simulationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics
  2. 2026Payoff scaling shapes cooperation in LLM agents across languages
  3. 2026Collective cooperation without individual fidelity in LLM agents
  4. 2025Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
  5. 2025Playing games with Large language models: Randomness and strategy
  6. 2026SODE: Analyzing Social Dynamics in LLM Agents
  7. 2025Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies
  8. 2025Evaluating LLMs in Open-Source Games