mlsanityData to 7 Oct 2026

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

arXiv 2305.14078 ↗First posted 23 May 2023cs.ROcited by 231

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

also in 1 more
Abstract (arXiv)

Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in addition to a policy that acts on it. The world model and the policy can be combined in a search algorithm, such as Monte Carlo Tree Search (MCTS), to scale up task planning. In our new LLM-MCTS algorithm, the LLM-induced world model provides a commonsense prior belief for MCTS to achieve effective reasoning; the LLM-induced policy acts as a heuristic to guide the search, vastly improving search efficiency. Experiments show that LLM-MCTS outperforms both MCTS alone and policies induced by LLMs (GPT2 and GPT3.5) by a wide margin, for complex, novel tasks. Further experiments and analyses on multiple tasks -- multiplication, multi-hop travel planning, object rearrangement -- suggest minimum description length (MDL) as a general guiding principle: if the description length of the world model is substantially smaller than that of the policy, using LLM as a world model for model-based planning is likely better than using LLM solely as a policy.

Key facts. Cited by 231 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 12 of its 43 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

12 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul

Other references · 11

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  6. 2023Planning with Large Language Models for Code Generationcited by 179
  7. 2020Rearrangement: A Challenge for Embodied AIcited by 153
  8. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 140
  9. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
  10. 2020Watch-And-Help: A Challenge for Social Perception and Human-AI Collaborationcited by 131
  11. 2019LeTS-Drive: Driving in a Crowd by Learning from Tree Searchcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 79; 2025: 99; 2026: 38.

231 papers.

Sort:

By area:

  1. 2024Understanding the planning of LLM agents: A surveycited by 414
  2. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  3. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  4. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  5. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  6. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  7. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
  8. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordiacited by 119
  9. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  10. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  11. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environmentcited by 99
  12. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 89
38 more
  1. 2024Large Language Models for Robotics: Opportunities, Challenges, and Perspectivescited by 88
  2. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  3. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  4. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  5. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  6. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 74
  7. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  8. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulationcited by 71
  9. 2026Scaling Reasoning Efficiently via Relaxed On-Policy Distillationcited by 71
  10. 2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributioncited by 68
  11. 2024Agent Planning with World Knowledge Modelcited by 66
  12. 2025WoW: Towards a World omniscient World model Through Embodied Interactioncited by 66
  13. 2024TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Samplingcited by 61
  14. 2023Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingcited by 59
  15. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  16. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  17. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  18. 2023Algorithm Evolution Using Large Language Modelcited by 52
  19. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 51
  20. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policycited by 51
  21. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  22. 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
  23. 2024Autoformulation of Mathematical Optimization Models Using LLMscited by 48
  24. 2023LangNav: Language as a Perceptual Representation for Navigationcited by 47
  25. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  26. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
  27. 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 43
  28. 2024Werewolf Arena: A Case Study in LLM Evaluation via Social Deductioncited by 42
  29. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  30. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  31. 2023CoPAL: Corrective Planning of Robot Actions with Large Language Modelscited by 39
  32. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  33. 2024Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Modelscited by 37
  34. 2024Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultracited by 36
  35. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 34
  36. 2024Benchmarks as Microscopes: A Call for Model Metrologycited by 33
  37. 2023Active Preference Inference using Language Models and Probabilistic Reasoningcited by 29
  38. 2023Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worldscited by 26

50 most cited of 231 All 231 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploring and Benchmarking the Planning Capabilities of Large Language Models
  2. 2025PlanU: Large Language Model Reasoning through Planning under Uncertainty
  3. 2023Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning
  4. 2026GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning
  5. 2025A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
  6. 2024Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
  7. 2024Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning
  8. 2025LLMs Can Plan Only If We Tell Them