在基于大语言模型的多智能体系统操作中管理不确定性
Managing Uncertainty in LLM-based Multi-Agent System Operation
AI总结：
本文提出了一种基于生命周期的不确定性管理框架，用于提升基于大语言模型的多智能体系统在安全关键领域的可靠性和可诊断性。
摘要：
在安全关键领域如寿命超声心动图中应用基于大语言模型的多智能体软件系统，引入了无法仅通过提高模型准确性来解决系统级风险。在系统运行过程中，除了个体LLM行为外，不确定性通过智能体协调、数据管道、人机交互和运行时控制逻辑传播。然而，现有工作大多将不确定性视为模型层面的问题，而非软件工程首要关注的问题。本文从系统级和运行时视角出发。我们首先区分了基于LLM的多智能体软件系统操作中的本体论和认识论不确定性。在此基础上，我们提出一个基于生命周期的不确定性管理框架，包含四个机制：表示、识别、演变和适应。不确定性生命周期管理如何在架构层和执行阶段中产生、转变和缓解，从而实现结构化的运行时治理和受控适应。我们通过在临床合作中开发的现实世界基于LLM的多智能体超声心动图软件系统演示了该框架的可行性，展示了在诊断推理中的改进可靠性和可诊断性。所提出的方法可推广到其他安全关键的基于LLM的多智能体软件系统，支持在模型中心方法之外的原则性操作控制和运行时保证。
英文摘要：
Applying LLM-based multi-agent software systems in safety-critical domains such as lifespan echocardiography introduces system-level risks that cannot be addressed by improving model accuracy alone. During system operation, beyond individual LLM behavior, uncertainty propagates through agent coordination, data pipelines, human-in-the-loop interaction, and runtime control logic. Yet existing work largely treats uncertainty at the model level rather than as a first-class software engineering concern. This paper approaches uncertainty from both system-level and runtime perspectives. We first differentiate epistemological and ontological uncertainties in the context of LLM-based multi-agent software system operation. Building on this foundation, we propose a lifecycle-based uncertainty management framework comprising four mechanisms: representation, identification, evolution, and adaptation. The uncertainty lifecycle governs how uncertainties emerge, transform, and are mitigated across architectural layers and execution phases, enabling structured runtime governance and controlled adaptation. We demonstrate the feasibility of the framework using a real-world LLM-based multi-agent echocardiographic software system developed in clinical collaboration, showing improved reliability and diagnosability in diagnostic reasoning. The proposed approach generalizes to other safety-critical LLM-based multi-agent software systems, supporting principled operational control and runtime assurance beyond model-centric methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
