MACIE: Multi-agent Causal Intelligence Explainer For Collective Behavior Understanding

Abstract

As Multi Agent Reinforcement Learning systems are used in safety critical applications. Understanding why agents make decisions and how they achieve collective behavior is crucial. Existing explainable AI methods struggle in multi agent settings. They fail to attribute collective outcomes to individuals, quantify emergent behaviors, or capture complex interactions. We present MACIE Multi Agent Causal Intelligence Explainer, a framework combining structural causal models, interventional counterfactuals, and Shapley values to provide comprehensive explanations. MACIE addresses three questions. First, each agent's causal contribution using interventional attribution scores. Second, system level emergent intelligence through synergy metrics separating collective effects from individual contributions. Third, actionable explanations using natural language narratives synthesizing causal insights. We evaluate MACIE across four MARL scenarios: cooperative, competitive, and mixed motive. Results

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyweinberg2025macie

Related papers

• MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning (2025)0.00
• Situation-dependent Causal Influence-based Cooperative Multi-agent Reinforcement Learning (2023)5.24
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• A Roadmap Towards Improving Multi-agent Reinforcement Learning With Causal Discovery And Inference (2025)0.00
• An Organizationally-oriented Approach To Enhancing Explainability And Control In Multi-agent Reinforcement Learning (2025)2.26
• Collective Explainable AI: Explaining Cooperative Strategies And Agent Contribution In Multiagent Reinforcement Learning With Shapley Values (2021)0.00
• Discovering Causality For Efficient Cooperation In Multi-agent Environments (2023)0.00
• MACCA: Offline Multi-agent Reinforcement Learning With Causal Credit Assignment (2023)0.00