Kamila Štekerová

This study investigates how linguistic framing influences the strategic behaviour of large language models in repeated interactions. Four models (Mistral, Qwen3, Llama3.2, Llama3.3) were embedded as autonomous agents in a simulation of a 25-round iterated prisoner's dilemma under three prompt conditions: neutral, positively biased, and hunger-framed. Although payoff structures remained constant, linguistic variation produced substantial behavioural divergence. A one-way analysis of variance showed significant prompt effects in 13 out of 16 model pairings (adjusted p < 0.05). Positively biased prompts increased cooperation by 4–9 percentage points, while survival-framed prompts increased cooperation up to 80 percentage points. While Qwen3 and Llama3.3 were highly sensitive to framing, Llama3.2 showed minimal responsiveness. Several models exhibited emergent strategies such as conditional cooperation and end-game defection. These findings indicate that subtle linguistic cues can systematically modulate cooperative behaviour in large language model agents.

The paper deals with the fusion of game theory and computational epidemiology. It presents an agent-based simulation that demonstrates how game theory principles can be used to study the effects of individual decision making in an epidemic situation. Our model of a symmetric repeated vaccination game with imperfect information was developed using NetLogo. Players decide whether or not to vaccinate by weighing the costs of vaccination against the potential costs of disease. The decisions of neighbors and the course of epidemic determine the costs. Different diseases and scenarios can be simulated by manipulating the model with input parameters. The model allows the number of infections, the number of players following a particular strategy, and the highest payouts for players in each of the three states. Four experiments were conducted.