mlsanityData to 7 Oct 2026

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

arXiv 2310.08582 ↗First posted 12 Oct 2023cs.CL cs.AI cs.LGcited by 48

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language Models (LLMs) to generate actions iteratively has become a prevalent paradigm due to its superior performance and user-friendliness. However, this paradigm is plagued by two inefficiencies: high token consumption and redundant error correction, both of which hinder its scalability for large-scale testing and applications. To address these issues, we propose Tree-Planner, which reframes task planning with LLMs into three distinct phases: plan sampling, action tree construction, and grounded deciding. Tree-Planner starts by using an LLM to sample a set of potential plans before execution, followed by the aggregation of them to form an action tree. Finally, the LLM performs a top-down decision-making process on the tree, taking into account real-time environmental information. Experiments show that Tree-Planner achieves state-of-the-art performance while maintaining high efficiency. By decomposing LLM queries into a single plan-sampling call and multiple grounded-deciding calls, a considerable part of the prompt are less likely to be repeatedly consumed. As a result, token consumption is reduced by 92.2% compared to the previously best-performing model. Additionally, by enabling backtracking on the action tree as needed, the correction process becomes more flexible, leading to a 40.5% decrease in error corrections.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 47 of its 62 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

47 of 62 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  2. 2023Reasoning with Language Model is Planning with World Model24 May
  3. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planning23 May

Other references · 44

  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. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  8. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  9. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  10. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  11. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  12. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
32 more
  1. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  2. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  3. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  4. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  5. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  6. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  7. 2023ChatGPT for Robotics: Design Principles and Model Abilitiescited by 296
  8. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 276
  9. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  10. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  11. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 193
  12. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  13. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  14. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
  15. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  16. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 147
  17. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 140
  18. 2023Batch Prompting: Efficient Inference with Large Language Model APIscited by 84
  19. 2023Embodied Task Planning with Large Language Modelscited by 84
  20. 2023ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Modelscited by 63
  21. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  22. 2023DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignmentcited by 58
  23. 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
  24. 2021A Systematic Investigation of Commonsense Knowledge in Large Language Modelscited by 56
  25. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  26. 2018Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systemscited by 40
  27. 2023Understanding the Capabilities of Large Language Models for Automated Planningcited by 34
  28. 2022On Grounded Planning for Embodied Tasks with Language Modelscited by 33
  29. 2019Regression Planning Networkscited by 32
  30. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  31. 2022Few-shot Subgoal Planning with Language Modelscited by 22
  32. 2023Robot Behavior-Tree-Based Task Generation with Large Language Modelscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 21; 2025: 22; 2026: 4.

48 papers.

Sort:

By area:

  1. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  2. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  3. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  4. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  5. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  6. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  7. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 117
  8. 2024Large Language Models Meet NLP: A Surveycited by 102
  9. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  10. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 84
  11. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  12. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
36 more
  1. 2023GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstrationcited by 76
  2. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  3. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 68
  4. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thoughtcited by 56
  5. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 55
  6. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  7. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
  8. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  9. 2024Tool-Planner: Task Planning with Clusters across Multiple Toolscited by 32
  10. 2024What Factors Affect Multi-Modal In-Context Learning? An In-Depth Explorationcited by 31
  11. 2024EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agentscited by 24
  12. 2024Multi-Agent Large Language Models for Conversational Task-Solvingcited by 24
  13. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 22
  14. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
  15. 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignmentcited by 19
  16. 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systemscited by 17
  17. 2025Virtual Agent Economiescited by 17
  18. 2024DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planningcited by 14
  19. 2024What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practicescited by 14
  20. 2024PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Modelscited by 11
  21. 2024VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actionscited by 8
  22. 2025Unveiling and Causalizing CoT: A Causal Pespectivecited by 6
  23. 2025Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraintscited by 6
  24. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 6
  25. 2024Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modelingcited by 4
  26. 2025Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learningcited by 4
  27. 2025Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimationcited by 4
  28. 2026The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoningcited by 4
  29. 2025EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Controlcited by 3
  30. 2025STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systemscited by 2
  31. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  32. 2026ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agentscited by 2
  33. 2025AINav: Large Language Model-Based Adaptive Interactive Navigationcited by 1
  34. 2025RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Taskscited by 1
  35. 2025Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Modelcited by 1
  36. 2026MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
  2. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  3. 2024When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
  4. 2025Cost-Awareness in Tree-Search LLM Planning: A Systematic Study
  5. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
  6. 2023ADaPT: As-Needed Decomposition and Planning with Language Models
  7. 2024HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning
  8. 2025STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner