# Large language models replicate and predict human cooperation across experiments in game theory

arXiv: https://arxiv.org/abs/2511.04500 · HTML: https://mlsanity.com/paper/2511.04500/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 90 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Prompt Design and Engineering: Introduction and Advanced Methods](https://mlsanity.com/paper/2401.14423/) (2024)
- [Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations](https://mlsanity.com/paper/2504.03274/) (2025)
- [Can AI with High Reasoning Ability Replicate Human-like Decision Making in Economic Experiments?](https://mlsanity.com/paper/2406.11426/) (2024)
- [Emergent LLM behaviors are observationally equivalent to data leakage](https://mlsanity.com/paper/2505.23796/) (2025)
- [Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models](https://mlsanity.com/paper/2510.11586/) (2025)
- [An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide](https://mlsanity.com/paper/2402.14837/) (2024)
- [Humans display a reduced set of consistent behavioral phenotypes in dyadic games](https://mlsanity.com/paper/1608.02015/) (2016)
- [Citizen Social Lab: A digital platform for human behaviour experimentation within a citizen science framework](https://mlsanity.com/paper/1807.00037/) (2018)
- [Preferences for efficiency, rather than preferences for morality, drive cooperation in the one-shot Stag-Hunt Game](https://mlsanity.com/paper/1908.03091/) (2019)

## Built on by (most cited first, 2 of 2)

- [Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems](https://mlsanity.com/paper/2606.07552/) (2026)
- [Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games](https://mlsanity.com/paper/2607.27536/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the social and behavioral sciences. Yet how closely LLMs mirror human decision-making remains poorly understood. This gap is critical: misalignment could produce harmful outcomes in practice, while failure to replicate human behavior renders LLMs ineffective as social simulators. Here, we address this gap by replicating large-scale game-theoretic experiments and by introducing a systematic prompting and probing framework for machine-behavioral evaluation. We test three open models typically used to power agents (Llama, Mistral, and Qwen). Across 121 dyadic games spanning four classical game types, Llama reproduces human cooperation patterns with high fidelity, while Qwen aligns closely with Nash equilibrium predictions. Characterizing models through behavioral phenotyping, we find that humans and Llama share an envious decision profile, while Qwen and Mistral exhibit different profiles. An attention-based analysis of payoff salience reveals Llama processes payoff information in a structured, layer-dependent manner absent in Qwen and Mistral, suggesting a mechanistic basis for its closer alignment with human behavior. Population-level behavioral replication is achieved without persona-based prompting, simplifying the simulation process. Extending the experimental parameter space beyond the original human-tested games, we generate and preregister testable hypotheses for novel game configurations. Our findings demonstrate appropriately configured LLMs can replicate aggregate human behavioral patterns, exhibit human-like decision phenotypes, and enable systematic exploration of unexplored experimental spaces, offering a complementary approach to traditional behavioral research that generates new empirical predictions about human social decision-making.