mlsanityData to 14 Oct 2026

Uncertainty in Action: Confidence Elicitation in Embodied Agents

arXiv 2503.10628 ↗First posted 13 Mar 2025cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 58 of its 82 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

58 of 82 references.

References · 58

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  8. 2022Emergent Abilities of Large Language Modelscited by 2,512
  9. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  10. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  11. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  12. 2023Mastering Diverse Domains through World Modelscited by 1,253
38 more
  1. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  3. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  5. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  8. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  9. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  10. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  11. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
  12. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  13. 2023FireAct: Toward Language Agent Fine-tuningcited by 256
  14. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 215
  15. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  16. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 203
  17. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  18. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  19. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 126
  20. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 122
  21. 2021Online Robust Reinforcement Learning with Model Uncertaintycited by 96
  22. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  23. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 86
  24. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 86
  25. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 84
  26. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 82
  27. 2022Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matterscited by 76
  28. 2024Explore until Confident: Efficient Exploration for Embodied Question Answeringcited by 74
  29. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 73
  30. 2023MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perceptioncited by 67
  31. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  32. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 54
  33. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  34. 2024Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Modelscited by 54
  35. 2024AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learningcited by 53
  36. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 36
  37. 2021The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Designcited by 33
  38. 2021Calibrated and Sharp Uncertainties in Deep Learning via Density Estimationcited by 33

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 20263D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decodingcited by 3
  2. 2026DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoisingcited by 2
  3. 2026GroundControl: Anticipating Navigation Failures in Vision-Language Agents via Trajectory-Consistent Uncertainty Estimatescited by 2
  4. 2026Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agentscited by 2
  5. 2025Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splattingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
  2. 2026Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
  3. 2025BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind
  4. 2026Explicit World Models for Reliable Human-Robot Collaboration
  5. 2026ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
  6. 2026Probing an Embodied LLM: When Higher Observation Fidelity Hurts Problem Solving
  7. 2026ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
  8. 2026The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents