multi-agent-simulation

This paper presents multi-agent simulations of the emergence of morphological alternation patterns (like 'go/went') in language, using an AI Historical Linguist (LLM-driven) to evaluate plausibility of evolved morphologies against real languages.

Introduces SovSim, a multi-agent simulation framework for studying cooperation and resource sustainability in LLM societies with asymmetric power structures. Experiments show that introducing a dominant agent (boss or king) severely degrades cooperation and survival rates across 11 state-of-the-art models.

This paper uses the Greenland sovereignty crisis as a case study to test LLM geopolitical behavior through multi-agent simulations, revealing that coercion framing increases escalation and that peaceful acquisition is rare.