Agents
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
arXiv:2604.14691v1 Announce Type: cross Abstract: LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often
arXiv:2604.14691v1 Announce Type: cross 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 extbf{extsc{CAMO}}, an automated extbf{Ca}usal discovery framework from extbf{M}icrextbf{o} behaviors to extbf{M}acrextbf{o} Emergence in LLM agent simulations. extsc{CAMO} converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target Y. extsc{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 extsc{CAMO}.
Related
- Form Without Function: Agent Social Behavior in the Moltbook Network
- OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora
- Emergent Social Structures in Autonomous AI Agent Networks: A Metadata Analysis of 626 Agents on the Pilot Protocol
Source: arXiv cs.CL | 2026-04-17