mlsanityData to 14 Oct 2026

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

arXiv 2604.14691 ↗First posted 16 Apr 2026cs.AI cs.CL cs.CYcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

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 Causal discovery framework from Micro behaviors to Macro 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 32 of its 67 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

32 of 67 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery18 Dec
  2. 2024Causal Agent based on Large Language Model13 Aug
  3. 2024Multi-Agent Causal Discovery Using Large Language Models21 Jul

Other references · 29

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2025Gemma 3 Technical Reportcited by 1,824
  4. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  5. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  6. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 150
  7. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  8. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  9. 2024Robust agents learn causal world modelscited by 81
  10. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 55
  11. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 53
  12. 2024Emergence of Social Norms in Generative Agent Societies: Principles and Architecturecited by 41
17 more
  1. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 32
  2. 2025LLM-based Human Simulations Have Not Yet Been Reliablecited by 30
  3. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  4. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunitiescited by 27
  5. 2025Emergence of polarization in networks of large language model agentscited by 26
  6. 2024Causality for Large Language Modelscited by 25
  7. 2025Emergent Coordination in Multi-Agent Language Modelscited by 23
  8. 2025Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoningcited by 17
  9. 2024Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theorycited by 16
  10. 2024On the Reliability of Large Language Models for Causal Discoverycited by 12
  11. 2024Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communitiescited by 12
  12. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
  13. 2024LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysiscited by 9
  14. 2025The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systemscited by 9
  15. 2025Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMscited by 3
  16. 2023Understanding Breast Cancer Survival: Using Causality and Language Models on Multi-omics Datacited by 1
  17. 2026Invariant Causal Routing for Governing Social Norms in Online Market Economiescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Variational Causal Dynamics: Discovering Modular World Models from Interventions
  2. 2026EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
  3. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
  4. 2026Attributing Emergence in Million-Agent Systems
  5. 2025Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior
  6. 2026Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
  7. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery
  8. 2025MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding