自动挖掘大模型智能体模拟中微观行为到宏观涌现的因果链
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
- 将机制假设转化为可计算因子，学习以宏观目标为中心的紧凑因果表示
- 输出可解释的因果链与可操作的干预节点，精准定位影响宏观结果的关键因素
- 通过反事实探测修正假设，适合研究社会涌现现象的科研人员使用
大模型驱动的智能体模拟被广泛用于研究社会涌现现象，但微观行为如何导致宏观结果的因果机制往往不清晰。这是由于涌现源于复杂的智能体交互、中观层面的反馈回路及非线性关系，使得生成机制难以解耦。为此，我们提出 extsc{CAMO}，一个从微观行为到宏观涌现的自动化因果发现框架。 extsc{CAMO} 将机制假设转化为基于模拟记录的可计算因子，学习以涌现目标 $Y$ 为中心的紧凑因果表示。它输出可计算的马尔可夫边界和最小上游解释子图，生成可解释的因果链条与可操作的干预杠杆。同时，利用模拟器内部的反事实探测来确定模糊边的方向，并在证据与当前假设矛盾时修订假设。四个涌现场景的实验验证了 extsc{CAMO} 的有效性。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。