{"ID":2850259,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22222","arxiv_id":"2510.22222","title":"CreditXAI: A Multi-Agent System for Explainable Corporate Credit Rating","abstract":"In the domain of corporate credit rating, traditional deep learning methods have improved predictive accuracy but still suffer from the inherent 'black-box' problem and limited interpretability. While incorporating non-financial information enriches the data and provides partial interpretability, the models still lack hierarchical reasoning mechanisms, limiting their comprehensive analytical capabilities. To address these challenges, we propose CreditXAI, a Multi-Agent System (MAS) framework that simulates the collaborative decision-making process of professional credit analysts. The framework focuses on business, financial, and governance risk dimensions to generate consistent and interpretable credit assessments. Experimental results demonstrate that multi-agent collaboration improves predictive accuracy by more than 7% over the best single-agent baseline, confirming its significant synergistic advantage in corporate credit risk evaluation. This study provides a new technical pathway to build intelligent and interpretable credit rating models.","short_abstract":"In the domain of corporate credit rating, traditional deep learning methods have improved predictive accuracy but still suffer from the inherent 'black-box' problem and limited interpretability. While incorporating non-financial information enriches the data and provides partial interpretability, the models still lack...","url_abs":"https://arxiv.org/abs/2510.22222","url_pdf":"https://arxiv.org/pdf/2510.22222v1","authors":"[\"Yumeng Shi\",\"Zhongliang Yang\",\"Yisi Wang\",\"Linna Zhou\"]","published":"2025-10-25T08:52:27Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CE\"]","methods":"[]","has_code":false}