Search papers, labs, and topics across Lattice.
This paper introduces CAMO, a framework for automated causal discovery in LLM agent simulations, designed to uncover micro-to-macro causal mechanisms underlying emergent phenomena. CAMO converts mechanistic hypotheses into computable factors, learns a compact causal representation centered on an emergent target, and uses counterfactual probing to refine causal relationships. Experiments across four emergent settings demonstrate that CAMO can identify interpretable causal chains and actionable intervention levers.
LLM agent simulations are no longer black boxes: CAMO reveals the hidden causal pathways from individual agent actions to emergent social behaviors.
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 \textbf{\textsc{CAMO}}, an automated \textbf{Ca}usal discovery framework from \textbf{M}icr\textbf{o} behaviors to \textbf{M}acr\textbf{o} Emergence in LLM agent simulations. \textsc{CAMO} converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target $Y$. \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 \textsc{CAMO}.
