用智能体AI自动发现企业破产的因果关系，结果更可靠且可解释。
ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI
- 通过大模型推理与统计检验迭代优化因果图结构
- 在企业破产数据上比现有方法更可靠
- 适合需要可解释因果分析的金融风控场景
本文提出ARCADIA，一种基于智能体AI的可扩展因果发现框架，融合大语言模型推理与统计诊断，构建有效且时间一致的因果结构。不同于传统算法，ARCADIA通过约束引导提示与因果有效性反馈，迭代优化候选有向无环图（DAG），生成稳定可解释的模型，适用于高风险现实场景。在企业破产数据上的实验表明，其因果图可靠性优于NOTEARS、GOLEM和DirectLiNGAM，同时提供完全可解释、可干预的分析流程。该框架展示了智能体大模型在自主科学建模与结构化因果推断中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。