mlsanityData to 14 Oct 2026

LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models

arXiv 2503.18971 ↗First posted 22 Mar 2025cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) excel in various natural language tasks but often struggle with long-horizon planning problems requiring structured reasoning. This limitation has drawn interest in integrating neuro-symbolic approaches within the Automated Planning (AP) and Natural Language Processing (NLP) communities. However, identifying optimal AP deployment frameworks can be daunting and introduces new challenges. This paper aims to provide a timely survey of the current research with an in-depth analysis, positioning LLMs as tools for formalizing and refining planning specifications to support reliable off-the-shelf AP planners. By systematically reviewing the current state of research, we highlight methodologies, and identify critical challenges and future directions, hoping to contribute to the joint research on NLP and Automated Planning.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 70 of its 126 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

70 of 126 references.

References · 70

  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  3. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  4. 2023StarCoder: may the source be with you!cited by 799
  5. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  6. 2024Understanding the planning of LLM agents: A surveycited by 421
  7. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  8. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  9. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  10. 2023Faithful Chain-of-Thought Reasoningcited by 288
  11. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 224
  12. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
38 more
  1. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
  2. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 141
  3. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 128
  4. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 113
  5. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 108
  6. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 103
  7. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 94
  8. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 89
  9. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 83
  10. 2024Planning In Natural Language Improves LLM Search For Code Generationcited by 83
  11. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  12. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  13. 2022Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning taskscited by 56
  14. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  15. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  16. 2024ACPBench: Reasoning about Action, Change, and Planningcited by 39
  17. 2024Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programmingcited by 35
  18. 2024Robust Planning with LLM-Modulo Framework: Case Study in Travel Planningcited by 34
  19. 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 33
  20. 2024Thought of Search: Planning with Language Models Through The Lens of Efficiencycited by 32
  21. 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Plannercited by 32
  22. 2024InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planningcited by 31
  23. 2023Vision-Language Interpreter for Robot Task Planningcited by 30
  24. 2023Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worldscited by 26
  25. 2023The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputscited by 23
  26. 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptionscited by 22
  27. 2024Making Large Language Models into World Models with Precondition and Effect Knowledgecited by 22
  28. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 20
  29. 2024On the Limit of Language Models as Planning Formalizerscited by 18
  30. 2024TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Plannerscited by 17
  31. 2024Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1cited by 17
  32. 2024Planning in the Dark: LLM-Symbolic Planning Pipeline without Expertscited by 16
  33. 2024PROC2PDDL: Open-Domain Planning Representations from Textscited by 15
  34. 2025LLMs Can Plan Only If We Tell Themcited by 15
  35. 2024PDDLEGO: Iterative Planning in Textual Environmentscited by 14
  36. 2024DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planningcited by 14
  37. 2024Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decompositioncited by 14
  38. 2018Extracting Action Sequences from Texts Based on Deep Reinforcement Learningcited by 12

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 23.

38 papers.

Sort:

By area:

  1. 2025Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworkscited by 40
  2. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 40
  3. 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Codecited by 18
  4. 2025Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planningcited by 15
  5. 2025Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policiescited by 7
  6. 2026PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environmentscited by 7
  7. 2026Using large language models for embodied planning introduces systematic safety riskscited by 5
  8. 2025Unifying Inference-Time Planning Language Generationcited by 3
  9. 2025Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Schedulingcited by 3
  10. 2025Vision Language Models Cannot Plan, but Can They Formalize?cited by 3
  11. 2025Language Model as Planner and Formalizer under Constraintscited by 3
  12. 2025Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLMcited by 2
26 more
  1. 2026Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcementcited by 2
  2. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  3. 2025Bridging Engineering and AI Planning through Model-Based Knowledge Transformation for the Validation of Automated Production System Variantscited by 1
  4. 2026Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisationcited by 1
  5. 2026Language Models as Higher-Order Planning Formalizerscited by 1
  6. 2026LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planningcited by 1
  7. 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agentscited by 1
  8. 2025Make Planning Research Rigorous Again!cited by 0
  9. 2025Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristicscited by 0
  10. 2025Autonomous Assessment of Generalizability of AI Agent Capabilitiescited by 0
  11. 2026Textual Planning with Explicit Latent Transitionscited by 0
  12. 2026Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertaintycited by 0
  13. 2026RAMP: Hybrid DRL for Online Learning of Numeric Action Modelscited by 0
  14. 2026Property-Guided LLM Program Synthesis for Planningcited by 0
  15. 2026Robust Asynchronous Planning via Auto-Formalizationcited by 0
  16. 2026From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generationcited by 0
  17. 2026QueryGraph: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generationcited by 0
  18. 2026Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agendacited by 0
  19. 2026A Neuro-Symbolic Approach to Strategy Synthesis for Strategic Logicscited by 0
  20. 2026Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedbackcited by 0
  21. 2026Planning with Transformers: Chain of Computation and Structured Context Windowscited by 0
  22. 2026PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Modelscited by 0
  23. 2026LLM-Only PDDL Domain Repair with Open-Weight Modelscited by 0
  24. 2026A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narrativescited by 0
  25. 2026Grounded Evaluation and Repair for NL-to-PDDL Problem Generationcited by 0
  26. 2026HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Modelscited by 0