让智能体学会在复杂环境中表达信心，提升决策可靠性。
Uncertainty in Action: Confidence Elicitation in Embodied Agents
- 用三类推理框架结构化智能体的自信评估。
- 在Minecraft中验证，思维链方法能改善信心校准。
- 揭示智能体在推断情境下仍难区分不确定性，适合研究具身智能者。
在动态多模态环境中，具身智能体的不确定性既来自感知也来自决策过程。本文首次研究开放场景下具身智能体的信心表达问题。提出‘信心引出策略’（Elicitation Policies），通过归纳、演绎和溯因推理结构化信心评估；同时引入‘执行策略’（Execution Policies），通过重解读情境、动作采样和假设推理增强信心校准。在Minecraft环境中的校准与故障预测任务测试表明，如思维链（Chain-of-Thoughts）等结构化推理方法可提升信心校准效果。然而研究发现，在溯因推理情境下仍存在难以区分不确定性的持续挑战，凸显需要更先进的具身信心表达机制。
原文摘要 · Abstract (English)
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.
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。