organizational behavior analysts

Abstract: Belief propagation in social networks depends on how trust and distrust jointly shape interpersonal influence. We develop a network model that treats trust and distrust as distinct but statistically coupled quantities. Their joint values determine the net trust and uncertainty of each relationship, and a neighbor can influence an agent only when both threshold conditions are satisfied. We show that the correlation between trust and distrust reshapes the transition between consensus and fragmentation by changing the availability of influential neighbors. Network connectivity also affects this transition, whereas degree heterogeneity has a more limited effect when networks have comparable mean degree. Moreover, the availability of influential neighbors alone does not determine the final consensus: correlations between relational properties and network degree can select agents with different degree compositions, altering the direction and magnitude of collective belief. Finally, we introduce a comfort index that quantifies the expected availability of influential neighbors and analytically links the joint trust-distrust structure to collective dynamics. Our results establish a mechanistic connection between relational structure, effective social influence, and emergent collective belief states.

Abstract: Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game, a toy model for studying the mechanisms of collective belief formation. Concretely, a hidden country flag defines the ground truth, and each bounded agent directly observes only a private crop but can exchange beliefs and weigh social evidence from peers. Despite its simplicity, the Flag Game reproduces rich collective phenomenology: non-monotonic scaling of performance with population size, accuracy gains from social-awareness prompting and team diversity, and strong effects of organizational structure. In particular, we identify that collective belief collapse at small population sizes turns into collective belief polarization as the population grows. This polarization causes the performance decline at large population sizes, but creates diversity in collective beliefs. Finally, we dissect the mechanisms underlying collective belief collapse and polarization with two complementary approaches. We first introduce social circuit attribution, a technique to predict which agent, and what view, matters most to collective dynamics, and verify its predictions by causal interventions on agents, tracing how agent patching changes collective outcomes. However, the efficacy of causal interventions on agents decreases as the population grows. We therefore develop a statistical mechanical theory for larger populations and verify that it matches the empirical phase diagram. Together, these results take a first step toward mechanistic swarm interpretability, a science of how the properties of individual agents and their communication give rise to emergent collective behavior.