mlsanityData to 7 Oct 2026

Generalized Planning in PDDL Domains with Pretrained Large Language Models

arXiv 2305.11014 ↗First posted 18 May 2023cs.AIcited by 139

Not on the map. Why?

Cited by 24 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

Key facts. Cited by 139 papers in the map (data through 7 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

35 of 60 references.

References · 35

  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. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  9. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  10. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  11. 2023Teaching Large Language Models to Self-Debugcited by 963
  12. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
23 more
  1. 2022PAL: Program-aided Language Modelscited by 635
  2. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  3. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  4. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  5. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  6. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
  7. 2023Self-planning Code Generation with Large Language Modelscited by 121
  8. 2021Skill Induction and Planning with Latent Languagecited by 99
  9. 2018Temporal Difference Models: Model-Free Deep RL for Model-Based Controlcited by 89
  10. 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 86
  11. 2020Inductive logic programming at 30: a new introductioncited by 83
  12. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  13. 2020Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictorscited by 60
  14. 2022Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning taskscited by 56
  15. 2022Predicate Invention for Bilevel Planningcited by 49
  16. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  17. 2023Conversational Automated Program Repaircited by 41
  18. 2020Generalized Planning With Deep Reinforcement Learningcited by 35
  19. 2022On Grounded Planning for Embodied Tasks with Language Modelscited by 33
  20. 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generationcited by 27
  21. 2018Features, Projections, and Representation Change for Generalized Planningcited by 25
  22. 2021Generalized Planning as Heuristic Searchcited by 18
  23. 2022PG3: Policy-Guided Planning for Generalized Policy Generationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 16; 2024: 53; 2025: 49; 2026: 21.

139 papers.

Sort:

By area:

  1. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  2. 2023Cognitive Architectures for Language Agentscited by 422
  3. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  4. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  5. 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMscited by 187
  6. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  7. 2023REFLECT: Summarizing Robot Experiences for Failure Explanation and Correctioncited by 171
  8. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  9. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  10. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
  11. 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
  12. 2024Vision Language Models are In-Context Value Learnerscited by 84
38 more
  1. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  2. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
  3. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  4. 2024Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detectioncited by 59
  5. 2025QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?cited by 56
  6. 2025Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgettingcited by 52
  7. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
  8. 2023BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biologycited by 42
  9. 2023Creative Robot Tool Use with Large Language Modelscited by 42
  10. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  11. 2024Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Tracescited by 40
  12. 2023Learning adaptive planning representations with natural language guidancecited by 36
  13. 2024VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Modelcited by 36
  14. 2024Grounding Multimodal Large Language Models in Actionscited by 35
  15. 2024DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Modelscited by 33
  16. 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 32
  17. 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Plannercited by 31
  18. 2024TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Modelscited by 29
  19. 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learningcited by 29
  20. 2024ReplanVLM: Replanning Robotic Tasks with Visual Language Modelscited by 28
  21. 2024EPO: Hierarchical LLM Agents with Environment Preference Optimizationcited by 28
  22. 2024ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoningcited by 27
  23. 2025Text2World: Benchmarking Large Language Models for Symbolic World Model Generationcited by 25
  24. 2024Steering Large Language Models between Code Execution and Textual Reasoningcited by 24
  25. 2024MaestroMotif: Skill Design from Artificial Intelligence Feedbackcited by 24
  26. 2023The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputscited by 23
  27. 2024A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddingscited by 23
  28. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  29. 2024Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptionscited by 22
  30. 2024To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planningcited by 21
  31. 2024Affordance-Guided Reinforcement Learning via Visual Promptingcited by 20
  32. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
  33. 2025VeriPlan: Integrating Formal Verification and LLMs into End-User Planningcited by 19
  34. 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Codecited by 18
  35. 2024Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Modelscited by 17
  36. 2023LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Modelcited by 15
  37. 2025Evaluating the Goal-Directedness of Large Language Modelscited by 15
  38. 2025LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Roboticscited by 15

50 most cited of 139 All 139 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
  2. 2026GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
  3. 2026Language Models as Higher-Order Planning Formalizers
  4. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
  5. 2025Generating Symbolic World Models via Test-time Scaling of Large Language Models
  6. 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions
  7. 2023On the Planning, Search, and Memorization Capabilities of Large Language Models
  8. 2025Bridging the Reasoning Gap: Small LLMs Can Plan with Generalised Strategies