Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
用于商业保险承保的具有对抗性自我批评的智能体人工智能
专题命中 代码与定理证明 :reasoning(abstract);分类 cs.AI、cs.LG
AI总结 研究针对商业保险承保中AI可靠性问题,提出含对抗性自我批评机制的人在回路智能体系统,开发故障模式分类法。实验表明该机制降低幻觉率、提高准确率,还确保人类权威,为受监管领域安全部署AI提供模型。
Comments 9 pages, 8 figuers, 6 tables, Presented at 9th International Conference on Modern Computing, Networking and Applications (MCNA2026)
Journal ref 2026 International Conference on Modern Computing, Networking and Applications (MCNA)