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

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 $\mathbf{\text{textsc}}\mathbf{\text{CAMO}}$, an automated $\mathbf{\text{Ca}}$usal discovery framework from $\mathbf{\text{M}}$icr$\mathbf{\text{o}}$ behaviors to $\mathbf{\text{M}}$acr$\mathbf{\text{o}}$ Emergence in LLM agent simulations. $\text{textsc}CAMO$ converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target $Y$. $\text{textsc}CAMO$ 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 $\text{textsc}CAMO$.