mlsanityData to 7 Oct 2026

Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity

arXiv 2402.06529 ↗First posted 9 Feb 2024cs.AI cs.CL cs.LGcited by 26

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper grounding. However, LLM hallucination may result in robots confidently executing plans that are misaligned with user goals or even unsafe in critical scenarios. Additionally, inherent ambiguity in natural language instructions can introduce uncertainty into the LLM's reasoning and planning processes.We propose introspective planning, a systematic approach that align LLM's uncertainty with the inherent ambiguity of the task. Our approach constructs a knowledge base containing introspective reasoning examples as post-hoc rationalizations of human-selected safe and compliant plans, which are retrieved during deployment. Evaluations on three tasks, including a newly introduced safe mobile manipulation benchmark, demonstrate that introspection substantially improves both compliance and safety over state-of-the-art LLM-based planning methods. Furthermore, we empirically show that introspective planning, in combination with conformal prediction, achieves tighter confidence bounds, maintaining statistical success guarantees while minimizing unnecessary user clarification requests. The webpage and code are accessible at https://introplan.github.io.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 45 of its 52 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

45 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners4 Jul
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul

Other references · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  11. 2022Emergent Abilities of Large Language Modelscited by 2,483
  12. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
31 more
  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  2. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  3. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  4. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  7. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  10. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  11. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  12. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  13. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  14. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  15. 2023Active Retrieval Augmented Generationcited by 506
  16. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  17. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  18. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  19. 2020Calibration of Pre-trained Transformerscited by 307
  20. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 270
  21. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  22. 2023Do Large Language Models Know What They Don't Know?cited by 238
  23. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 210
  24. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  25. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  26. 2023REFLECT: Summarizing Robot Experiences for Failure Explanation and Correctioncited by 171
  27. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  28. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  29. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  30. 2023Prompting Large Language Models With the Socratic Methodcited by 43
  31. 2022Task Ambiguity in Humans and Language Modelscited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 16; 2026: 9.

26 papers.

Sort:

By area:

  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  2. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  3. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  4. 2025Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robotscited by 17
  5. 2026Learning Personalized Agents from Human Feedbackcited by 16
  6. 2025RLHS: Mitigating Misalignment in RLHF with Hindsight Simulationcited by 15
  7. 2025When Two LLMs Debate, Both Think They'll Wincited by 10
  8. 2025ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guaranteescited by 9
  9. 2025Agentic LLM Framework for Adaptive Decision Discoursecited by 6
  10. 2025AI Awarenesscited by 6
  11. 2025Uncertainty in Action: Confidence Elicitation in Embodied Agentscited by 5
  12. 2025CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Humancited by 5
14 more
  1. 2025SafePath: Conformal Prediction for Safe LLM-Based Autonomous Navigationcited by 4
  2. 2025Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimationcited by 4
  3. 2024A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreementcited by 3
  4. 2025INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Modelscited by 3
  5. 2025Open-Ended Goal Inference through Actions and Language for Human-Robot Collaborationcited by 3
  6. 20263D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTScited by 2
  7. 2026End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agentcited by 1
  8. 2025CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planningcited by 0
  9. 2026Learning Transferable Latent User Preferences for Human-Aligned Decision Makingcited by 0
  10. 2026Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skillscited by 0
  11. 2026Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaborationcited by 0
  12. 2026ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigationcited by 0
  13. 2026Actively Resolving Contextual Uncertainty for Underspecified Tasks in Natural Languagecited by 0
  14. 2026Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Using large language models for embodied planning introduces systematic safety risks
  2. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  3. 2025Constrained Natural Language Action Planning for Resilient Embodied Systems
  4. 2024MultiTalk: Introspective and Extrospective Dialogue for Human-Environment-LLM Alignment
  5. 2025SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
  6. 2026Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues
  7. 2025RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation
  8. 2024SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models