mlsanityData to 7 Oct 2026

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

arXiv 2305.14909 ↗First posted 24 May 2023cs.AIcited by 204

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

Abstract (arXiv)

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong reliance on feedback from interactions with simulators or even the actual environment, and the inefficiency in utilizing human feedback. In this work, we introduce a novel alternative paradigm that constructs an explicit world (domain) model in planning domain definition language (PDDL) and then uses it to plan with sound domain-independent planners. To address the fact that LLMs may not generate a fully functional PDDL model initially, we employ LLMs as an interface between PDDL and sources of corrective feedback, such as PDDL validators and humans. For users who lack a background in PDDL, we show that LLMs can translate PDDL into natural language and effectively encode corrective feedback back to the underlying domain model. Our framework not only enjoys the correctness guarantee offered by the external planners but also reduces human involvement by allowing users to correct domain models at the beginning, rather than inspecting and correcting (through interactive prompting) every generated plan as in previous work. On two IPC domains and a Household domain that is more complicated than commonly used benchmarks such as ALFWorld, we demonstrate that GPT-4 can be leveraged to produce high-quality PDDL models for over 40 actions, and the corrected PDDL models are then used to successfully solve 48 challenging planning tasks. Resources, including the source code, are released at: https://guansuns.github.io/pages/llm-dm.

Key facts. Cited by 204 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 34 of its 59 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

34 of 59 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling28 Jan
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul
  3. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learning8 Oct
  4. 2020Language Models are Few-Shot Learners28 May

Other references · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  6. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  7. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  8. 2022A Generalist Agentcited by 802
  9. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  10. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  11. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  12. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
18 more
  1. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  2. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  3. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  4. 2023Faithful Chain-of-Thought Reasoningcited by 285
  5. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  6. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  7. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
  8. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)cited by 85
  9. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  10. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  11. 2021Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systemscited by 36
  12. 2022LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulationcited by 32
  13. 2021GPT3-to-plan: Extracting plans from text using GPT-3cited by 26
  14. 2022Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversitycited by 22
  15. 2018Discovering Underlying Plans Based on Shallow Modelscited by 9
  16. 2020Can Transformers Reason About Effects of Actions?cited by 9
  17. 2023Planning with Sequence Models through Iterative Energy Minimizationcited by 8
  18. 2022MACQ: A Holistic View of Model Acquisition Techniquescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 78; 2025: 74; 2026: 43.

204 papers.

Sort:

By area:

  1. 2023Cognitive Architectures for Language Agentscited by 422
  2. 2024Understanding the planning of LLM agents: A surveycited by 414
  3. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  4. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  5. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
  6. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  7. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
  8. 2024Evaluating the World Model Implicit in a Generative Modelcited by 107
  9. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  10. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environmentcited by 99
  11. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 95
  12. 2024Can Large Language Models Reason and Plan?cited by 82
38 more
  1. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  2. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  3. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  4. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  5. 20253D and 4D World Modeling: A Surveycited by 64
  6. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  7. 2024RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulationcited by 48
  8. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  9. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 45
  10. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  11. 2023CoPAL: Corrective Planning of Robot Actions with Large Language Modelscited by 39
  12. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  13. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchcited by 38
  14. 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
  15. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  16. 2024VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Modelcited by 36
  17. 2023Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Modelscited by 35
  18. 2024Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programmingcited by 35
  19. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 34
  20. 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 32
  21. 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Plannercited by 31
  22. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agentscited by 31
  23. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 30
  24. 2025Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoningcited by 29
  25. 2024ReplanVLM: Replanning Robotic Tasks with Visual Language Modelscited by 28
  26. 2024Planning with Multi-Constraints via Collaborative Language Agentscited by 26
  27. 2025World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planningcited by 26
  28. 2025Text2World: Benchmarking Large Language Models for Symbolic World Model Generationcited by 25
  29. 2025PoE-World: Compositional World Modeling with Products of Programmatic Expertscited by 25
  30. 2024WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agentscited by 24
  31. 2024Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviorscited by 23
  32. 2024A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddingscited by 23
  33. 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptionscited by 22
  34. 2024Making Large Language Models into World Models with Precondition and Effect Knowledgecited by 21
  35. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
  36. 2025Implicit Language Models are RNNs: Balancing Parallelization and Expressivitycited by 21
  37. 2024Exploring and Benchmarking the Planning Capabilities of Large Language Modelscited by 19
  38. 2025VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Modelcited by 19

50 most cited of 204 All 204 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs
  2. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  3. 2025One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration
  4. 2025Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
  5. 2025End-to-end PDDL Planning with Hardcoded and Dynamic Agents
  6. 2025Toward PDDL Planning Copilot
  7. 2025LLMs Can Plan Only If We Tell Them
  8. 2025A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream