让大模型在多步决策中动态评估不确定性，提升智能体可靠性。
SAUP: Situation Awareness Uncertainty Propagation on LLM Agent
- 通过逐步传播机制追踪大模型推理中的不确定性
- 在基准数据集上提升20%的AUROC指标表现
- 适合需要高可靠性的复杂决策系统开发者
将大语言模型集成到多步智能体系统中，可实现跨多种应用的复杂决策。然而，其输出往往缺乏可靠性，因此不确定性估计至关重要。现有方法主要关注最终步骤的输出不确定性，未能考虑多步决策过程中的累积不确定性以及智能体与环境之间的动态交互。为此，我们提出SAUP（情境感知不确定性传播）框架，通过在每一步推理中传播不确定性，并引入情境权重来反映不同步骤的不确定性影响。该方法兼容多种单步不确定性估计技术，能提供更全面、准确的不确定性度量。在多个基准数据集上的大量实验表明，SAUP显著优于现有最先进方法，在AUROC指标上最高提升20%。
原文摘要 · Abstract (English)
Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process. SAUP incorporates situational awareness by assigning situational weights to each step's uncertainty during the propagation. Our method, compatible with various one-step uncertainty estimation techniques, provides a comprehensive and accurate uncertainty measure. Extensive experiments on benchmark datasets demonstrate that SAUP significantly outperforms existing state-of-the-art methods, achieving up to 20% improvement in AUROC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。