行动中的不确定性：具身智能体中的置信度诱导
Uncertainty in Action: Confidence Elicitation in Embodied Agents
AI总结：
本文研究具身智能体在动态多模态环境中的置信度表达问题，提出结合三类推理的诱导策略与执行策略，并在 Minecraft 中验证结构化推理可改善校准，但溯因不确定性识别仍具挑战。
摘要：
对于在动态多模态环境中导航的具身智能体而言，表达置信度颇具挑战，因为不确定性同时源于感知和决策过程。我们提出首个研究开放式多模态环境中具身置信度诱导的工作。我们引入了 Elicitation Policies（诱导策略），围绕归纳、演绎和溯因推理来组织置信度评估；同时引入 Execution Policies（执行策略），通过场景重释、动作采样和假设推理来增强置信度校准。在 Minecraft 环境中评估智能体的校准和失败预测任务时，我们表明，诸如 Chain-of-Thoughts（思维链）等结构化推理方法能够改善置信度校准。然而，研究结果也揭示，在区分不确定性方面仍存在持续挑战，尤其是在溯因情境下，这凸显了开发更复杂的具身置信度诱导方法的必要性。
英文摘要：
Expressing confidence is challenging for embodied agents navigating dynamic multimodal environments, where uncertainty arises from both perception and decision-making processes. We present the first work investigating embodied confidence elicitation in open-ended multimodal environments. We introduce Elicitation Policies, which structure confidence assessment across inductive, deductive, and abductive reasoning, along with Execution Policies, which enhance confidence calibration through scenario reinterpretation, action sampling, and hypothetical reasoning. Evaluating agents in calibration and failure prediction tasks within the Minecraft environment, we show that structured reasoning approaches, such as Chain-of-Thoughts, improve confidence calibration. However, our findings also reveal persistent challenges in distinguishing uncertainty, particularly under abductive settings, underscoring the need for more sophisticated embodied confidence elicitation 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。
