CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations

arXiv:2604.14691v1 Announce Type: new
Abstract: LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent interactions and meso-level feedback and nonlinearity, making generative mechanisms hard to disentangle. To this end, we introduce textbftextscCAMO, an automated textbfCausal discovery framework from textbfMicrtextbfo behaviors to textbfMacrtextbfo Emergence in LLM agent simulations. textscCAMO converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target $Y$. textscCAMO outputs a computable Markov boundary and a minimal upstream explanatory subgraph, yielding interpretable causal chains and actionable intervention levers. It also uses simulator-internal counterfactual probing to orient ambiguous edges and revise hypotheses when evidence contradicts the current view. Experiments across four emergent settings demonstrate the promise of textscCAMO.