📄 中文摘要
商业保险承保是一个劳动密集型的过程，需要对大量文档进行人工审核以评估风险并确定保单定价。尽管人工智能在效率上有显著提升，但现有解决方案缺乏全面的推理能力和确保可靠性的内部机制，尤其是在受监管的高风险环境中。完全自动化在需要人类判断和问责的场景中仍然不切实际且不可取。该研究提出了一种决策负向的人机协作代理系统，结合了对抗性自我批评机制，作为受监管承保工作流程的有限安全架构。在该系统中，批评代理会挑战主要代理的决策，以提高整体决策的可靠性和安全性。
具有对抗性自我批评的商业保险承保代理人工智能
📄 English Summary
Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
Commercial insurance underwriting is a labor-intensive process that necessitates manual review of extensive documentation to assess risk and determine policy pricing. While AI provides significant efficiency gains, existing solutions often lack comprehensive reasoning capabilities and internal mechanisms to ensure reliability in regulated, high-stakes environments. Full automation remains impractical and inadvisable in scenarios where human judgment and accountability are essential. This study proposes a decision-negative, human-in-the-loop agentic system that integrates an adversarial self-critique mechanism as a bounded safety architecture for regulated underwriting workflows. Within this framework, a critic agent interrogates the decisions of the primary agent, enhancing the overall reliability and safety of the decision-making process.