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.
@article{arxiv.2510.22222,
title = {CreditXAI: A Multi-Agent System for Explainable Corporate Credit Rating},
author = {Yumeng Shi and Zhongliang Yang and Yisi Wang and Linna Zhou},
journal= {arXiv preprint arXiv:2510.22222},
year = {2025}
}