mlsanityData to 7 Oct 2026

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

arXiv 2502.11221 ↗First posted 16 Feb 2025cs.AI cs.CLcited by 82

Not on the map. Why?

Cited by 37 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state. A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying. However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks. There is also a lack of clear and consistent evaluation criteria. Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap. It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency. For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses. Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 90 of its 124 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

90 of 124 references.

References · 90

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  8. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  10. 2021Convex optimizationcited by 2,479
  11. 2024A Survey on LLM-as-a-Judgecited by 1,384
  12. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
38 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  3. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  4. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  5. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  6. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  7. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  9. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  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. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  13. 2024Understanding the planning of LLM agents: A surveycited by 414
  14. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  15. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  16. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  17. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 354
  18. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  19. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  20. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  21. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  22. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  23. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  24. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 204
  25. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  26. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  27. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  28. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  29. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  30. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 139
  31. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 138
  32. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  33. 2023SmartPlay: A Benchmark for LLMs as Intelligent Agentscited by 123
  34. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
  35. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  36. 2021Skill Induction and Planning with Latent Languagecited by 99
  37. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 93
  38. 2024Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrappingcited by 89

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 41; 2026: 41.

82 papers.

Sort:

By area:

  1. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  2. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  3. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  4. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Sciencecited by 20
  5. 2025MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimizationcited by 12
  6. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  7. 2026MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systemscited by 11
  8. 2025Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Servicescited by 10
  9. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  10. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 10
  11. 2025Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactionscited by 9
  12. 2025AutoTool: Efficient Tool Selection for Large Language Model Agentscited by 9
38 more
  1. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  2. 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learningcited by 7
  3. 2025Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoningcited by 7
  4. 2025What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignmentcited by 7
  5. 2025Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learningcited by 7
  6. 2025HARBOR: Exploring Persona Dynamics in Multi-Agent Competitioncited by 6
  7. 2025Toward Super Agent System with Hybrid AI Routerscited by 6
  8. 2025PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilitiescited by 6
  9. 2025A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Userscited by 6
  10. 2025BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Constructioncited by 6
  11. 2026Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learningcited by 6
  12. 2026Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agentscited by 6
  13. 2025Cost-Awareness in Tree-Search LLM Planning: A Systematic Studycited by 5
  14. 2025Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspectivecited by 5
  15. 2025A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysiscited by 5
  16. 2025DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shapingcited by 5
  17. 2026Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contextscited by 4
  18. 2026TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agentscited by 4
  19. 2026Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agentscited by 4
  20. 2026Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planningcited by 4
  21. 2025Unifying Inference-Time Planning Language Generationcited by 3
  22. 2025Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Riskscited by 3
  23. 2025Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Datacited by 3
  24. 2025Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extractioncited by 3
  25. 2025Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMscited by 3
  26. 2025Language Model as Planner and Formalizer under Constraintscited by 3
  27. 2025Idea2Plan: Exploring AI-Powered Research Planningcited by 3
  28. 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelscited by 3
  29. 2025NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Taskscited by 2
  30. 2025Vision Language Models Cannot Plan, but Can They Formalize?cited by 2
  31. 2025SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agentscited by 2
  32. 2026Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoningcited by 2
  33. 2026SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Modelscited by 2
  34. 2026Verifiable Reasoning for LLM-based Generative Recommendationcited by 2
  35. 2026RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Executioncited by 2
  36. 2026Plover: Steering GUI Agents through Plan-Centric Interactioncited by 2
  37. 2025LLMs Between the Nodes: Community Discovery Beyond Vectorscited by 1
  38. 2025Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planningcited by 1

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Models for Planning: A Comprehensive and Systematic Survey
  2. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)
  3. 2024Plancraft: an evaluation dataset for planning with LLM agents
  4. 2024A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
  5. 2025A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
  6. 2024FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
  7. 2025COMPASS: Benchmarking Constrained Optimization in LLM Agents
  8. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks