{"ID":2888837,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22758","arxiv_id":"2507.22758","title":"MASCA: LLM based-Multi Agents System for Credit Assessment","abstract":"Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling. However, credit assessment remains an underexplored challenge, traditionally dependent on rule-based methods and statistical models. In this paper, we introduce MASCA, an LLM-driven multi-agent system designed to enhance credit evaluation by mirroring real-world decision-making processes. The framework employs a layered architecture where specialized LLM-based agents collaboratively tackle sub-tasks. Additionally, we integrate contrastive learning for risk and reward assessment to optimize decision-making. We further present a signaling game theory perspective on hierarchical multi-agent systems, offering theoretical insights into their structure and interactions. Our paper also includes a detailed bias analysis in credit assessment, addressing fairness concerns. Experimental results demonstrate that MASCA outperforms baseline approaches, highlighting the effectiveness of hierarchical LLM-based multi-agent systems in financial applications, particularly in credit scoring.","short_abstract":"Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling. However, credit assessment remains an underexplored challenge, traditionally dependent on rule-based methods and statistical models. In this paper, we introduce MASCA, an...","url_abs":"https://arxiv.org/abs/2507.22758","url_pdf":"https://arxiv.org/pdf/2507.22758v1","authors":"[\"Gautam Jajoo\",\"Pranjal A Chitale\",\"Saksham Agarwal\"]","published":"2025-07-30T15:19:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CE\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}