Task and Motion Planning with Large Language Models for Object Rearrangement
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
Multi-object rearrangement is a crucial skill for service robots, and commonsense reasoning is frequently needed in this process. However, achieving commonsense arrangements requires knowledge about objects, which is hard to transfer to robots. Large language models (LLMs) are one potential source of this knowledge, but they do not naively capture information about plausible physical arrangements of the world. We propose LLM-GROP, which uses prompting to extract commonsense knowledge about semantically valid object configurations from an LLM and instantiates them with a task and motion planner in order to generalize to varying scene geometry. LLM-GROP allows us to go from natural-language commands to human-aligned object rearrangement in varied environments. Based on human evaluations, our approach achieves the highest rating while outperforming competitive baselines in terms of success rate while maintaining comparable cumulative action costs. Finally, we demonstrate a practical implementation of LLM-GROP on a mobile manipulator in real-world scenarios. Supplementary materials are available at: https://sites.google.com/view/llm-grop
Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. First posted on arXiv 10 Mar 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 37; 2024: 56; 2025: 30; 2026: 17.
140 papers.
Sort:
By area:
- 2023Reasoning with Language Model is Planning with World Modelcited by 846
- 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
- 2023A Comprehensive Overview of Large Language Modelscited by 639
- 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
- 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
- 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
- 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
- 2023Large Language Models as General Pattern Machinescited by 196
- 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
- 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
- 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
- 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
38 more
- 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
- 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
- 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2023Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planningcited by 88
- 2024Large Language Models for Robotics: Opportunities, Challenges, and Perspectivescited by 88
- 2024Vision Language Models are In-Context Value Learnerscited by 84
- 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
- 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
- 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
- 2023GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstrationcited by 76
- 2024LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoningcited by 63
- 2024Human-Object Interaction from Human-Level Instructionscited by 62
- 2024Real-World Robot Applications of Foundation Models: A Reviewcited by 60
- 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 55
- 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoningcited by 49
- 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
- 2024Guiding Long-Horizon Task and Motion Planning with Vision Language Modelscited by 46
- 2024VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulationcited by 43
- 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 43
- 2023Creative Robot Tool Use with Large Language Modelscited by 42
- 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
- 2023CoPAL: Corrective Planning of Robot Actions with Large Language Modelscited by 39
- 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
- 2024DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Modelscited by 33
- 2024VLMPC: Vision-Language Model Predictive Control for Robotic Manipulationcited by 32
- 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learningcited by 29
- 2023Interactive Planning Using Large Language Models for Partially Observable Robotics Taskscited by 27
- 2023Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worldscited by 26
- 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
- 2024RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulationcited by 24
- 2023Grounding Classical Task Planners via Vision-Language Modelscited by 23
- 2024Tools Fail: Detecting Silent Errors in Faulty Toolscited by 23
- 2024RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-Worldcited by 22
- 2023Conformal Temporal Logic Planning using Large Language Modelscited by 21
- 2024LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actionscited by 21
- 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
- 2024Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfactioncited by 19
50 most cited of 140 All 140 (JSON)
- 2026ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim27 Sep 2026
- 2026HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models15 Sep 2026
- 2026Leveraging Inter-object Affordances for Efficient Planning in Contact-rich Tasks26 Aug 2026
- 2026Temporal Logic Guided Universal Task Representations for Reinforcement Learning16 Aug 2026
- 2026Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills3 Aug 2026
- 2026SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs2 Aug 2026
- 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels28 Jul 2026
- 2026ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation20 Jul 2026
- 2026EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics21 Jun 2026
- 2026Learning Transferable Latent User Preferences for Human-Aligned Decision Making12 May 2026
- 2026Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents12 May 2026
- 2026Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement24 Mar 2026
38 more
- 2026Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences13 Mar 2026
- 2026RACAS: Controlling Diverse Robots With a Single Agentic System5 Mar 2026
- 2026Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning4 Mar 2026
- 2026RobotDesignGPT: Automated Robot Design Synthesis using Vision Language Models16 Jan 2026
- 2026Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Model Queries7 Jan 2026
- 2025SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding14 Dec 2025
- 2025LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator11 Dec 2025
- 2025CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning9 Nov 2025
- 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning4 Nov 2025
- 2025EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making14 Oct 2025
- 2025Population-Coded Spiking Neural Networks for High-Dimensional Robotic Control12 Oct 2025
- 2025Information Seeking for Robust Decision Making under Partial Observability2 Oct 2025
- 2025Human Centric General Physical Intelligence for Agile Manufacturing Automation16 Aug 2025
- 2025PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation8 Aug 2025
- 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks3 Aug 2025
- 2025Enhancing Decision-Making of Large Language Models via Actor-Critic4 Jun 2025
- 2025Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planning3 Jun 2025
- 2025From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control28 May 2025
- 2025RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving17 May 2025
- 2025ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning17 May 2025
- 2025Leveraging Pre-trained Large Language Models with Refined Prompting for Online Task and Motion Planning30 Apr 2025
- 2025MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems23 Apr 2025
- 2025Vision-Language Model Predictive Control for Manipulation Planning and Trajectory Generation7 Apr 2025
- 2025DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models4 Apr 2025
- 2025HierRelTriple: Guiding Indoor Layout Generation with Hierarchical Relationship Triplet Losses26 Mar 2025
- 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models22 Mar 2025
- 2025LLM+MAP: Bimanual Robot Task Planning using Large Language Models and Planning Domain Definition Language21 Mar 2025
- 2025ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control15 Mar 2025
- 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy13 Mar 2025
- 2025Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation3 Mar 2025
- 2025Structured Preference Optimization for Vision-Language Long-Horizon Task Planning28 Feb 2025
- 2025Combining Large Language Models and Symbolic Reasoning for Multi-Robot Temporal Planning through Explainable Knowledge Bases26 Feb 2025
- 2025NatSGLD: A Dataset with Speech, Gesture, Logic, and Demonstration for Robot Learning in Natural Human-Robot Interaction23 Feb 2025
- 2025A Survey on Large Language Models for Automated Planning18 Feb 2025
- 2025Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments4 Feb 2025
- 2024LLM-guided Task and Motion Planning using Knowledge-based Reasoning10 Dec 2024
- 2024DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline2 Dec 2024
- 2024RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World29 Nov 2024
50 newest of 140 All 140 (JSON)
- 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
- 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
- 2024LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoningcited by 63
- 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoningcited by 49
- 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
- 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 43
- 2023LgTS: Dynamic Task Sampling using LLM-generated sub-goals for Reinforcement Learning Agentscited by 11
- 2024Evaluating Vision-Language Models as Evaluators in Path Planningcited by 6
- 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Taskscited by 6
- 2024DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelinecited by 5
- 2026Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agentscited by 3
- 2025Combining Large Language Models and Symbolic Reasoning for Multi-Robot Temporal Planning through Explainable Knowledge Basescited by 2
12 most cited of 18 All 18 (JSON)
- 2026Learning Transferable Latent User Preferences for Human-Aligned Decision Making12 May 2026
- 2026Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents12 May 2026
- 2026Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences13 Mar 2026
- 2026Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Model Queries7 Jan 2026
- 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks3 Aug 2025
- 2025Combining Large Language Models and Symbolic Reasoning for Multi-Robot Temporal Planning through Explainable Knowledge Bases26 Feb 2025
- 2024LLM-guided Task and Motion Planning using Knowledge-based Reasoning10 Dec 2024
- 2024DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline2 Dec 2024
- 2024Evaluating Vision-Language Models as Evaluators in Path Planning27 Nov 2024
- 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models23 Sep 2024
- 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation1 Aug 2024
- 2024Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning5 Apr 2024
12 newest of 18 All 18 (JSON)
- 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
- 2024Large Language Models for Robotics: Opportunities, Challenges, and Perspectivescited by 88
- 2024Vision Language Models are In-Context Value Learnerscited by 84
- 2023GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstrationcited by 76
- 2024Real-World Robot Applications of Foundation Models: A Reviewcited by 60
- 2024Guiding Long-Horizon Task and Motion Planning with Vision Language Modelscited by 46
- 2024VLMPC: Vision-Language Model Predictive Control for Robotic Manipulationcited by 32
- 2023Grounding Classical Task Planners via Vision-Language Modelscited by 23
- 2023Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Modelscited by 16
- 2024DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planningcited by 14
- 2024PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Modelscited by 11
- 2024Open-World Task and Motion Planning via Vision-Language Model Generated Constraintscited by 9
12 most cited of 17 All 17 (JSON)
- 2026HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models15 Sep 2026
- 2026RobotDesignGPT: Automated Robot Design Synthesis using Vision Language Models16 Jan 2026
- 2025Vision-Language Model Predictive Control for Manipulation Planning and Trajectory Generation7 Apr 2025
- 2024Open-World Task and Motion Planning via Vision-Language Model Generated Constraints13 Nov 2024
- 2024Vision Language Models are In-Context Value Learners7 Nov 2024
- 2024LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation7 Oct 2024
- 2024Guiding Long-Horizon Task and Motion Planning with Vision Language Models3 Oct 2024
- 2024D-RMGPT: Robot-assisted collaborative tasks driven by large multimodal models21 Aug 2024
- 2024VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation13 Jul 2024
- 2024DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning25 Jun 2024
- 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interaction27 Feb 2024
- 2024PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models26 Feb 2024
12 newest of 17 All 17 (JSON)
- 2023Creative Robot Tool Use with Large Language Modelscited by 42
- 2023LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systemscited by 17
- 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policycited by 12
- 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planningcited by 10
- 2024AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agentscited by 8
- 2024Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineeringcited by 7
- 2023Conceptual Framework for Autonomous Cognitive Entitiescited by 6
- 2023RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction taskscited by 3
- 2024GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidancecited by 2
- 2026RACAS: Controlling Diverse Robots With a Single Agentic Systemcited by 2
- 2025LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operatorcited by 0
- 2026RACAS: Controlling Diverse Robots With a Single Agentic System5 Mar 2026
- 2025LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator11 Dec 2025
- 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning4 Nov 2025
- 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy13 Mar 2025
- 2024Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering16 Oct 2024
- 2024GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidance9 Oct 2024
- 2024AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agents11 May 2024
- 2023LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems14 Dec 2023
- 2023RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks27 Nov 2023
- 2023Creative Robot Tool Use with Large Language Models19 Oct 2023
- 2023Conceptual Framework for Autonomous Cognitive Entities3 Oct 2023
- 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
- 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learningcited by 29
- 2025Structured Preference Optimization for Vision-Language Long-Horizon Task Planningcited by 7
- 2024SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Enginecited by 1
- 2025Structured Preference Optimization for Vision-Language Long-Horizon Task Planning28 Feb 2025
- 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning18 Oct 2024
- 2024SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine25 Mar 2024
- 2023Eureka: Human-Level Reward Design via Coding Large Language Models19 Oct 2023
- 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
- 2023A Comprehensive Overview of Large Language Modelscited by 639
- 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
- 2023Large Language Models as General Pattern Machinescited by 196
- 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
- 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
- 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
- 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
- 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2023Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planningcited by 88
- 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
12 most cited of 85 All 85 (JSON)
- 2026ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim27 Sep 2026
- 2026Leveraging Inter-object Affordances for Efficient Planning in Contact-rich Tasks26 Aug 2026
- 2026Temporal Logic Guided Universal Task Representations for Reinforcement Learning16 Aug 2026
- 2026Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills3 Aug 2026
- 2026SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs2 Aug 2026
- 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels28 Jul 2026
- 2026ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation20 Jul 2026
- 2026EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics21 Jun 2026
- 2026Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement24 Mar 2026
- 2026Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning4 Mar 2026
- 2025SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding14 Dec 2025
- 2025CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning9 Nov 2025
12 newest of 85 All 85 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2025Learn from the Past: Language-conditioned Object Rearrangement with Large Language Models
- 2025MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
- 2025A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
- 2022Open-vocabulary Queryable Scene Representations for Real World Planning
- 2026Language Movement Primitives: Grounding Language Models in Robot Motion
- 2025OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints
- 2026Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning ↗
- 2025Physically Ground Commonsense Knowledge for Articulated Object Manipulation with Analytic Concepts