MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding

TL;DR

MACIE is a comprehensive framework that explains multi-agent reinforcement learning behaviors by combining causal models, counterfactuals, and Shapley values, enabling detailed attribution and emergent behavior analysis.

Contribution

It introduces MACIE, a novel explainability framework that uniquely integrates causal inference, emergence metrics, and natural language explanations for multi-agent systems.

Findings

Accurate attribution of agent contributions with mean phi_i of 5.07

Detection of positive emergence in cooperative tasks

Efficient computation at 0.79 seconds per dataset

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 show accurate outcome attribution, mean phi_i equals 5.07, standard deviation less than 0.05, detection of positive emergence in cooperative tasks, synergy index up to 0.461, and efficient computation, 0.79 seconds per dataset on CPU. MACIE uniquely combines causal rigor, emergence quantification, and multi agent support while remaining practical for real time use. This represents a step toward interpretable, trustworthy, and accountable multi agent AI.