RAINO: Anchoring Agents in Reality, A Systematic Review and Conceptual Framework for Realism in Agent-Based Modelling

Researchers present RAINO, a systematic framework addressing how realism is poorly defined and inconsistently operationalized in Agent-Based Models. The framework identifies Reality Anchors (empirical data, theory, expert knowledge) and their application as inputs or outputs, providing a conceptual foundation for evaluating and developing more realistic computational models.

Agent-Based Modelling (ABM) has become increasingly vital for simulating complex systems across finance, economics, and social science, yet the field lacks standardized approaches to defining and measuring realism. This paper addresses a significant theoretical gap by conducting a systematic literature review that exposes how realism remains ambiguous and poorly operationalized across existing ABM research. The authors demonstrate that while practitioners employ diverse methodologies to achieve realistic outcomes, they rarely justify why specific approaches suit their purposes, creating inconsistency and potentially undermining model validity.

The RAINO framework represents an important contribution by establishing common language around realism assessment. By categorizing Reality Anchors—sources of empirical grounding like data, formal theories, and expert judgment—and their deployment as model inputs or outputs, researchers can now systematize discussions about what makes models realistic. This matters particularly for financial modelling and cryptocurrency simulation, where agent behavior and market dynamics directly influence real asset valuations. Different stakeholders (academics, practitioners, regulators) may prioritize different anchors, explaining why identical models receive divergent credibility assessments.

For AI and computational finance communities, this framework enables more rigorous model development and peer review. Teams can explicitly articulate which reality anchors justify their architectural choices, improving transparency and reproducibility. In the crypto space specifically, better-theorized ABM approaches could enhance market simulation accuracy and risk assessment. The framework's recognition that realism is multidimensional rather than binary prevents false confidence in oversimplified models.

• →RAINO framework systematizes how realism is conceptualized in Agent-Based Models through Reality Anchors and their application as inputs or outputs
• →Existing ABM literature poorly defines realism, creating inconsistency in how models are evaluated and developed across disciplines
• →Different stakeholders assess model realism differently depending on which Reality Anchors they prioritize, explaining subjective credibility judgments
• →The framework improves transparency by requiring explicit justification of architectural choices grounded in empirical data, theory, or expert knowledge
• →Enhanced ABM realism assessment is particularly valuable for financial simulation and cryptocurrency market modeling applications