Exploring Causal Mechanisms with Generative Agent-Based Models

2026-09-21

AI Summary

This study addresses the unclear causal mechanisms through which individual behavioral rules give rise to emergent collective phenomena. To this end, it proposes RePair, a framework that translates natural language rules into quantifiable generative agent behaviors, constructs simulated worlds via simulation calibration, and implements matching interventions to trace the association between behavioral trajectories and causal processes. This work contributes a systematic mapping from qualitative rules to quantitative collective effects while achieving convergence in cross-rule comparisons. Furthermore, it validates the efficacy of natural language-driven causal inference, offering a reliable and interpretable methodological guide for exploring complex social phenomena.

Abstract

In this paper, we explore using generative agent-based models for a classical ABM application: testing how individual-level behavioral rules produce collective phenomena. We introduce RePair, a method that calibrates simulation worlds, operationalizes candidate mechanisms as natural-language rules, estimates their effects through matched interventions, and examines behavioral traces. We assess the method by testing it in four simulation worlds grounded in established social-science models and empirical studies. Our results reveal that (1) natural-language rules can produce measurable collective effects; (2) rule comparisons can converge as configurations accumulate; and (3) behavioral traces connect collective effects to agents' actions and interactions, helping researchers evaluate the proposed causal process. Together, these findings show the feasibility of using generative agent-based models to explore causal mechanisms and provide practical guidance for producing reliable, interpretable explanations.

Problem

• Generative Agent-Based Models
• Causal Mechanisms
• Collective Phenomena
• Behavioral Rules
• Simulation

Innovation

• Generative Agent-Based Models
• Causal Mechanisms
• Natural-Language Rules
• Matched Interventions
• Behavioral Traces