{"ID":2834866,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00839","arxiv_id":"2512.00839","title":"ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.00839","url_pdf":"https://arxiv.org/pdf/2512.00839v1","authors":"[\"Fabrizio Maturo\",\"Donato Riccio\",\"Andrea Mazzitelli\",\"Giuseppe Bifulco\",\"Francesco Paolone\",\"Iulia Brezeanu\"]","published":"2025-11-30T11:21:29Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"stat.CO\",\"stat.ME\"]","methods":"[\"Large Language Model\"]","has_code":false}