Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations

TL;DR

This study uses LLM-driven agent simulations to causally analyze how realistic and symbolic threats influence intergroup conflict, revealing that realistic threats directly escalate hostility while symbolic threats do so indirectly through ingroup bias.

Contribution

It introduces a novel simulation approach with LLM agents to causally disentangle the effects of realistic and symbolic threats on intergroup hostility over time.

Findings

Realistic threat directly increases hostility.

Symbolic threat effects are mediated by ingroup bias.

Non-hostile contact buffers escalation.

Abstract

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.