mlsanityData to 14 Oct 2026

Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension

arXiv 2605.29874 ↗First posted 28 May 2026cs.MA cs.AI cs.GTcited by 0

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

Abstract (arXiv)

Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibrium behaviour in competitive multi-agent settings? Willis et al. established a benchmark for this question using evolutionary game theory and the Iterated Prisoner's Dilemma (IPD), finding consistent cooperative biases in ChatGPT-4o and Claude 3.5 Sonnet. We extend this benchmark to four frontier models released in 2025-2026 - Claude Sonnet 4.6, Gemini 2.5 Flash, Gemini 3.1 Pro, and GPT-5.4 Mini - applying the identical protocol across three prompting styles (Default, Prose, Self-Refine) and four population compositions (balanced and biased, with and without noise). Cooperative bias persists across providers (H1): ten of twelve model-prompt combinations favour cooperative equilibria in balanced noiseless conditions. Cross-provider divergence is substantial (H3): Gemini 2.5 Flash reaches up to 77% aggressive equilibria under biased conditions, while GPT-5.4 Mini reaches 70% cooperative equilibria under Self-Refine. Support for aggressive capability parity is partial (H2): Self-Refine raises ICD in all models and Gemini 3.1 Pro Refine achieves the highest ICD in the dataset (0.925), but Default and Prose prompts show no systematic narrowing. Evidence on noise robustness is directionally positive but not robustly confirmed (H4): with n=500 Moran iterations per condition, average noise sensitivity is about 6 percentage points for Claude Sonnet 4.6 versus 13 pp for Claude 3.5 Sonnet, but this cross-study gap is not statistically significant once the predecessor's unreported sampling error is propagated. Provider identity, rather than model generation, is the strongest correlate of equilibrium outcomes; noise remains a universal challenge regardless of model size or vintage.

Key facts. No citing papers in the map yet (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 12 of its 31 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

12 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Evaluating Collective Behaviour of Hundreds of LLM Agents18 Feb
  2. 2024Cultural Evolution of Cooperation among LLM Agents13 Dec
  3. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 9

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  6. 2023Playing repeated games with Large Language Modelscited by 217
  7. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  8. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 92
  9. 2016An open reproducible framework for the study of the iterated prisoner's dilemmacited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma
  2. 2026Not a Monolith: Lab-Level Divergence in the Cooperative Equilibria of Chinese Frontier LLM Agents
  3. 2026Payoff scaling shapes cooperation in LLM agents across languages
  4. 2026Collective cooperation without individual fidelity in LLM agents
  5. 2025Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies
  6. 2026Group Selection Promotes Prosocial Prompts in Populations of LLM Agents
  7. 2025Group size effects and collective misalignment in LLM multi-agent systems
  8. 2026Emergence of Reputation-Based Cooperation in LLM Agents