mlsanityData to 14 Oct 2026

Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning

arXiv 2503.07323 ↗First posted 10 Mar 2025cs.AI cs.CV cs.ROcited by 2

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments, significantly surpassing first and recent seminal but limited studies on LLM's spatial reasoning, where movements are restricted in four directions in simple, static environments in the presence of only single agents much less multiple agents. Specifically, we investigate LLMs as spatial reasoners to overcome these limitations by uniformly encoding environments (e.g., real indoor floorplans), agents which can be dynamic obstacles and their paths as discrete tokens akin to language tokens. Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning. We show that LLMs can generalize across agents, tasks, and environments using only text-based interactions, opening new possibilities for semantically grounded, interactive navigation in both simulation and embodied systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 41 of its 45 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

41 of 45 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning17 Jan
  2. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  3. 2024Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models4 Apr
  4. 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning5 Oct
  5. 2022Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning30 Oct

Other references · 36

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  9. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  10. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  11. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 251
  12. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
24 more
  1. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  2. 2019Multi-Agent Pathfinding: Definitions, Variants, and Benchmarkscited by 199
  3. 2023Large Language Models as General Pattern Machinescited by 197
  4. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  5. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  6. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 127
  7. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
  8. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  9. 2023Synthesizing Physical Character-Scene Interactionscited by 104
  10. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  11. 2020Lifelong Multi-Agent Path Finding in Large-Scale Warehousescited by 80
  12. 2024Generating Human Interaction Motions in Scenes with Text Controlcited by 80
  13. 2021SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoningcited by 77
  14. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  15. 2024Motion-Agent: A Conversational Framework for Human Motion Generation with LLMscited by 47
  16. 2024Can Graph Learning Improve Planning in LLM-based Agents?cited by 43
  17. 2019Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Controlcited by 40
  18. 2024Multi-Robot Motion Planning with Diffusion Modelscited by 38
  19. 2024CoMA: Compositional Human Motion Generation with Multi-modal Agentscited by 19
  20. 2024SCENIC: Scene-aware Semantic Navigation with Instruction-guided Controlcited by 13
  21. 2025From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Taskcited by 10
  22. 2024Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Compositioncited by 9
  23. 2024Multi-Agent Path Finding in Continuous Spaces with Projected Diffusion Modelscited by 8
  24. 2024Look Further Ahead: Testing the Limits of GPT-4 in Path Planningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 11
  2. 2026Evaluating Few-Shot Temporal Reasoning of LLMs for Human Activity Prediction in Smart Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
  2. 2026From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?
  3. 2024LLM-Enhanced Path Planning: Safe and Efficient Autonomous Navigation with Instructional Inputs
  4. 2024Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models
  5. 2026Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents
  6. 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
  7. 2026Language Movement Primitives: Grounding Language Models in Robot Motion
  8. 2025From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning