发表机构
Swissi Institute for AI（Swissi人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种结合经济理论与制度设计的正式多智能体架构，用于在奥地利和德国受监管保险公司中实现合规、可审计的企业级AI，涵盖偿付能力监管II和《人工智能法案》等框架。
AI 中文摘要
本文提出了一种在受监管保险公司中实施企业级AI的正式多智能体架构，将经济理论与制度设计相结合。该框架综合了三个核心理论视角：利用阿罗（Arrow）的风险分担理论来形式化不确定性下的风险转化，利用纳什均衡（Nash equilibrium）来建模决策智能体之间的战略互动，以及利用委托-代理理论（Principal-Agent theory）来解决信息不对称下的激励对齐问题。保险公司被建模为一个在偿付能力、法律、ESG和运营边界下运行的约束优化实体，并特别关注奥地利和德国的监管环境。该架构将公司分解为多个专门智能体，每个智能体代表不同的功能领域，如资本管理、承保、理赔处理、合规、欺诈检测和客户互动。通过分层访问控制系统集成人在环（human-in-the-loop）智能体，确保基于用户角色的差异化数据可见性和决策影响力。一个编排智能体监督智能体间的协调，在偿付能力监管II、《人工智能法案》和保险分销指令等框架下执行监管可接受性和制度一致性。协议集成基于异步执行和双层通信基础设施，具体包括模型上下文协议（Model Context Protocol, MCP）和智能体间（Agent-to-Agent, A2A）消息传递。这种结构使得能够系统性地设计符合奥地利和德国金融机构制度逻辑的合规、可审计的多智能体系统。
英文摘要
This paper proposes a formal multi-agent architecture for implementing enterprise AI in regulated insurance firms, integrating economic theory with institutional design. The framework synthesises three core theoretical perspectives: Arrow's risk pooling theory to formalise risk transformation under uncertainty, Nash equilibrium to model strategic interactions between decision agents, and Principal-Agent theory to address incentive alignment under information asymmetry. The insurer is modelled as a constrained optimisation entity operating under solvency, legal, ESG, and operational boundaries, with specific focus on the regulatory contexts of Austria and Germany. The architecture decomposes the firm into multiple specialised agents, each representing distinct functional domains such as capital management, underwriting, claims processing, compliance, fraud detection, and client interaction. Human-in-the-loop agents are integrated through a tiered access control system, ensuring differentiated data visibility and decision influence based on user roles. An orchestrator agent supervises inter-agent coordination, enforcing regulatory admissibility and institutional coherence under frameworks such as Solvency II, the AI Act, and the Insurance Distribution Directive. Protocol integration is based on asynchronous execution and dual-layer communication infrastructures, specifically the Model Context Protocol (MCP) and Agent-to-Agent (A2A) messaging. This structure enables the systematic design of compliant, auditable multi-agent systems aligned with the institutional logic of financial firms in Austria and Germany.
Comments15 pages, 0 figures. Published in Swissi AI Journal under CC BY 4.0
Journal refSwissi AI Journal, Volume 2025, Article SAIJ-qzvrl4bwy7y2 (2025)
