ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI
This work addresses the need for stable and interpretable causal models in high-stakes domains such as corporate finance, though it appears incremental as it builds on existing causal discovery techniques with agentic enhancements.
The paper tackles the problem of causal discovery in corporate bankruptcy analysis by introducing ARCADIA, an agentic AI framework that integrates large-language-model reasoning with statistical diagnostics, resulting in more reliable causal graphs than existing methods like NOTEARS, GOLEM, and DirectLiNGAM.
This paper introduces ARCADIA, an agentic AI framework for causal discovery that integrates large-language-model reasoning with statistical diagnostics to construct valid, temporally coherent causal structures. Unlike traditional algorithms, ARCADIA iteratively refines candidate DAGs through constraint-guided prompting and causal-validity feedback, leading to stable and interpretable models for real-world high-stakes domains. Experiments on corporate bankruptcy data show that ARCADIA produces more reliable causal graphs than NOTEARS, GOLEM, and DirectLiNGAM while offering a fully explainable, intervention-ready pipeline. The framework advances AI by demonstrating how agentic LLMs can participate in autonomous scientific modeling and structured causal inference.