Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations
This provides a causal, dynamic analysis of conflict mechanisms for social science, though it is incremental in using simulations to address methodological barriers.
The study investigated how realistic and symbolic threats drive intergroup conflict using LLM-driven agent simulations, finding that realistic threat directly increases hostility while symbolic threat effects are weaker and mediated by ingroup bias, with non-hostile contact buffering escalation.
Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce temporal data. We address these barriers using simulations of large language model (LLM)-driven agents in virtual societies, independently varying realistic and symbolic threat while tracking actions, language, and attitudes. Representational analyses show that the underlying LLM encodes realistic threat, symbolic threat, and hostility as distinct internal states, that our manipulations map onto them, and that steering these states causally shifts behavior. Our simulations provide a causal account of threat-driven conflict over time: realistic threat directly increases hostility, whereas symbolic threat effects are weaker, fully mediated by ingroup bias, and increase hostility only when realistic threat is absent. Non-hostile intergroup contact buffers escalation, and structural asymmetries concentrate hostility among majority groups.