mlsanityData to 7 Oct 2026

Statler: State-Maintaining Language Models for Embodied Reasoning

arXiv 2306.17840 ↗First posted 30 Jun 2023cs.RO cs.CLcited by 40

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and observations. In this paper, we explore a new dimension in which large language models may benefit robotics planning. In particular, we propose Statler, a framework in which large language models are prompted to maintain an estimate of the world state, which are often unobservable, and track its transition as new actions are taken. Our framework then conditions each action on the estimate of the current world state. Despite being conceptually simple, our Statler framework significantly outperforms strong competing methods (e.g., Code-as-Policies) on several robot planning tasks. Additionally, it has the potential advantage of scaling up to more challenging long-horizon planning tasks.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 48 of its 81 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

48 of 81 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought22 Jun
  2. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning24 May
  3. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Models18 May
  4. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul
  5. 2020Language Models are Few-Shot Learners28 May

Other references · 43

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  11. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  12. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
31 more
  1. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  2. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  3. 2021Measuring Coding Challenge Competence With APPScited by 879
  4. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  5. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  6. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  7. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  8. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  9. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  10. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  11. 2022CodeT: Code Generation with Generated Testscited by 369
  12. 2022Visual Language Maps for Robot Navigationcited by 362
  13. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 337
  14. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  15. 2019Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Taskscited by 177
  16. 2020Improving Vision-and-Language Navigation with Image-Text Pairs from the Webcited by 177
  17. 2022Language Models of Code are Few-Shot Commonsense Learnerscited by 160
  18. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  19. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  20. 2021FILM: Following Instructions in Language with Modular Methodscited by 119
  21. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  22. 2021Do Long-Range Language Models Actually Use Long-Range Context?cited by 92
  23. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)cited by 85
  24. 2021Chess as a Testbed for Language Model State Trackingcited by 69
  25. 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 67
  26. 2018Interactive Visual Grounding of Referring Expressions for Human-Robot Interactioncited by 55
  27. 2015Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequencescited by 50
  28. 2022Leveraging Language for Accelerated Learning of Tool Manipulationcited by 26
  29. 2023Programmatically Grounded, Compositionally Generalizable Robotic Manipulationcited by 26
  30. 2023Autoregressive Modeling with Lookahead Attentioncited by 7
  31. 2022Learning to Reason With Relational Abstractionscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 13; 2025: 5; 2026: 17.

40 papers.

Sort:

By area:

  1. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  2. 2023Large Language Models for Robotics: A Surveycited by 132
  3. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  4. 2024Large Language Models for Robotics: Opportunities, Challenges, and Perspectivescited by 88
  5. 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulationcited by 72
  6. 2025A Comprehensive Survey on World Models for Embodied AIcited by 65
  7. 2024Real-World Robot Applications of Foundation Models: A Reviewcited by 60
  8. 2023Enhancing Recommender Systems with Large Language Model Reasoning Graphscited by 52
  9. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policycited by 51
  10. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  11. 2023CoPAL: Corrective Planning of Robot Actions with Large Language Modelscited by 39
  12. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 37
28 more
  1. 2024VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Modelcited by 36
  2. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingcited by 21
  3. 2024Symbolic Working Memory Enhances Language Models for Complex Rule Applicationcited by 17
  4. 2024Transcrib3D: 3D Referring Expression Resolution through Large Language Modelscited by 10
  5. 2025From Screens to Scenes: A Survey of Embodied AI in Healthcarecited by 10
  6. 2024A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Futurecited by 9
  7. 2026Towards the Harness of Embodied Agentscited by 7
  8. 2023Dobby: A Conversational Service Robot Driven by GPT-4cited by 4
  9. 2024Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMscited by 4
  10. 2024Organizing a Society of Language Models: Structures and Mechanisms for Enhanced Collective Intelligencecited by 3
  11. 2026Deriving Character Logic from Storyline as Codified Decision Treescited by 3
  12. 2026Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planningcited by 3
  13. 2025L3M+P: Lifelong Planning with Large Language Modelscited by 2
  14. 2026Reward Prediction with Factorized World Statescited by 2
  15. 2026ECHO: Continuous Hierarchical Memory for Vision-Language-Action Modelscited by 2
  16. 2025MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Modelscited by 1
  17. 2026Codified Finite-state Machines for Role-playingcited by 1
  18. 2026Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agentscited by 1
  19. 2024Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigationcited by 0
  20. 2025Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoningcited by 0
  21. 2026Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoningcited by 0
  22. 2026BOOKMARKS: Efficient Active Storyline Memory for Role-playingcited by 0
  23. 2026Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skillscited by 0
  24. 2026What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agentscited by 0
  25. 2026Embedding Large Language Models into Flow Controls: An Agentic Framework for Adaptive and Trustworthy Automated Cookingcited by 0
  26. 2026STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaborationcited by 0
  27. 2026In-Context Binding Capacity in Language Modelscited by 0
  28. 2026Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks
  2. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  3. 2026PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulation
  4. 2025Constrained Natural Language Action Planning for Resilient Embodied Systems
  5. 2026Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
  6. 2023Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning
  7. 2025A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
  8. 2025Combining Large Language Models and Symbolic Reasoning for Multi-Robot Temporal Planning through Explainable Knowledge Bases