mlsanityData to 14 Oct 2026

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

arXiv 2503.21696 ↗First posted 27 Mar 2025cs.CL cs.CVcited by 44

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with environments through image action interleaved trajectories remains largely -unexplored. We present Embodied Reasoner, a model that extends o1 style reasoning to interactive embodied search tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k interactive images and 90k diverse thinking processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training pipeline that progressively enhances the model's capabilities through imitation learning, self-exploration via rejection sampling, and self-correction through reflection tuning. The evaluation shows that our model significantly outperforms those advanced visual reasoning models, e.g., it exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9%, 24%, and +13%. Analysis reveals our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world environments also show our superiority while exhibiting fewer repeated searches and logical inconsistency cases.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 103 of its 133 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

103 of 133 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning18 Mar
  2. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  3. 2024NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning12 Mar
  4. 2023See and Think: Embodied Agent in Virtual Environment26 Nov
  5. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought24 May
  6. 2023Collaborating with language models for embodied reasoning1 Feb
  7. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul

Other references · 96

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  11. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  12. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
38 more
  1. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  2. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  3. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  6. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  8. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  9. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  10. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  11. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  12. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  13. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  14. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  15. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  16. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  17. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 454
  18. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  19. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  20. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  21. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
  22. 2022Visual Language Maps for Robot Navigationcited by 365
  23. 2023An Embodied Generalist Agent in 3D Worldcited by 365
  24. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  25. 2023ChatGPT for Robotics: Design Principles and Model Abilitiescited by 299
  26. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  27. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  28. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 239
  29. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 224
  30. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 221
  31. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 211
  32. 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thoughtcited by 206
  33. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  34. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  35. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 164
  36. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  37. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 153
  38. 2025LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMscited by 147

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 29; 2026: 15.

44 papers.

Sort:

By area:

  1. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  2. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  3. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 55
  4. 2025VLA-R1: Enhancing Reasoning in Vision-Language-Action Modelscited by 38
  5. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 31
  6. 2025RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaborationcited by 28
  7. 2025ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Modelscited by 27
  8. 2025Robix: A Unified Model for Robot Interaction, Reasoning and Planningcited by 23
  9. 2025WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learningcited by 21
  10. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 15
  11. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  12. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
32 more
  1. 2026Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Explorationcited by 13
  2. 2025ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representationscited by 12
  3. 2025Reinforced Reasoning for Embodied Planningcited by 12
  4. 2025Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Groundingcited by 10
  5. 2025ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learningcited by 10
  6. 2025BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learningcited by 9
  7. 2025Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videoscited by 8
  8. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 7
  9. 2025EmbodiedBrain: Expanding Performance Boundaries of Task Planning for Embodied Intelligencecited by 4
  10. 2025PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environmentscited by 4
  11. 2025LookPlanGraph: Embodied Instruction Following Method with VLM Graph Augmentationcited by 3
  12. 2026Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meterscited by 3
  13. 2025ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learningcited by 2
  14. 2026MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representationcited by 2
  15. 2026What if? Emulative Simulation with World Models for Situated Reasoningcited by 2
  16. 2026Are Video Reasoning Models Ready to Go Outside?cited by 2
  17. 2026Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representationscited by 2
  18. 2025CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMscited by 1
  19. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  20. 2025RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learningcited by 1
  21. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  22. 2025ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulationcited by 1
  23. 2026EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoningcited by 1
  24. 2026EAGLE-360: Embodied Active Global-to-Local Exploration in 360^circcited by 1
  25. 2025D3Grasp: Diverse and Deformable Dexterous Grasping for General Objectscited by 0
  26. 2025EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuningcited by 0
  27. 2026VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigationcited by 0
  28. 2026Why MLLMs Struggle to Determine Object Orientationscited by 0
  29. 2026VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulationcited by 0
  30. 2026UniETP: Unifying Environments for Generalizable Embodied Task Planningcited by 0
  31. 2026PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMscited by 0
  32. 2026EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning
  2. 2025EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
  3. 2025ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
  4. 2025UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces
  5. 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
  6. 2025REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories
  7. 2026ParallelWorld: Test-Time Scaling for Embodied Reasoning
  8. 2026ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution