用多智能体优化大模型债务谈判，提升决策理性与效率
Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent
- 设计13项指标的评估框架，量化大模型谈判表现
- 发现大模型易过度让步，谈判结果不如人类
- 提出MADeN框架，结合规划与判断模块提升决策质量
债务催收谈判（DCN）对管理不良贷款（NPL）和降低债权人损失至关重要。传统方法依赖人工，而大语言模型（LLMs）具备自动化潜力。然而，现有系统缺乏动态谈判与实时决策能力。本文探索了LLMs在自动化DCN中的应用，提出一个包含13个指标、覆盖4个维度的新评估框架。实验表明，相较于人类谈判者，LLMs倾向于过度让步。为解决此问题，我们提出多智能体债务谈判（MADeN）框架，集成规划与判断模块以提升决策合理性，并采用后训练技术（包括带拒绝采样的DPO）优化性能。研究为从业者与研究人员提供了提升该领域效率与结果的重要洞见。
原文摘要 · Abstract (English)
Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) and reducing creditor losses. Traditional methods are labor-intensive, while large language models (LLMs) offer promising automation potential. However, prior systems lacked dynamic negotiation and real-time decision-making capabilities. This paper explores LLMs in automating DCN and proposes a novel evaluation framework with 13 metrics across 4 aspects. Our experiments reveal that LLMs tend to over-concede compared to human negotiators. To address this, we propose the Multi-Agent Debt Negotiation (MADeN) framework, incorporating planning and judging modules to improve decision rationality. We also apply post-training techniques, including DPO with rejection sampling, to optimize performance. Our studies provide valuable insights for practitioners and researchers seeking to enhance efficiency and outcomes in this domain.
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。