SAUP: Situation Awareness Uncertainty Propagation on LLM Agent
This addresses uncertainty estimation for LLM agents in complex decision-making, though it is incremental as it builds on existing one-step techniques.
The paper tackles the problem of unreliable outputs in multistep LLM agent systems by proposing SAUP, a framework that propagates uncertainty through each reasoning step with situational awareness, resulting in up to 20% improvement in AUROC over existing methods.
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.