发表机构
University of Hull（赫尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于大语言模型的多智能体系统在精算风险建模中的不确定性量化，提出含中央枢纽的多智能体框架，用令牌级对数概率和贝叶斯网络进行不确定性传播，再现基线性能并提供工作流稳定性等见解。
AI 中文摘要
本文研究基于大语言模型（LLMs）的多智能体系统（MAS）如何支持精算风险建模，尤其关注不确定性量化。精算工作流程是高风险决策支持场景，不可靠输出会导致错误风险评估等问题。为解决LLMs概率性质及智能体间依赖引入的不确定性，提出多智能体框架，其中专业智能体在中央枢纽下执行数据准备等任务。主要贡献是使用令牌级对数概率和贝叶斯网络的不确定性传播新方法。将长度归一化对数概率摘要转换为校准后的任务级置信估计再纳入贝叶斯网络。结果表明该框架再现了基线精算性能，还能深入了解工作流程稳定性和运行时不确定性传播。
英文摘要
This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focus on uncertainty quantification. Actuarial workflows represent a high-stakes decision-support setting where unreliable outputs may lead to incorrect risk assessment, unfair pricing, and regulatory non-compliance. To address uncertainty introduced by the probabilistic nature of LLMs and dependencies between agents, a multi-agent framework is proposed in which specialised agents perform data preparation, modelling, review, and explanation tasks under a central hub. The main contribution is a novel approach to uncertainty propagation using token-level log-probabilities and a Bayesian Network. Importantly, log probabilities are not treated as direct probabilities of correctness or task success. Instead, length-normalised log-probability summaries are transformed into calibrated task-level confidence estimates before incorporation into the Bayesian Network. Results show that the framework reproduces baseline actuarial performance while providing additional insight into workflow stability and runtime uncertainty propagation.
CommentsThis paper got accepted for Ninth International Workshop on Artificial Intelligence Safety Engineering (WAISE 2026): https://www.waise.org/
