mlsanityData to 7 Oct 2026

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

arXiv 2412.11974 ↗First posted 16 Dec 2024cs.RO cs.AI cs.CLcited by 45

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning, Emma-X. Emma-X leverages our constructed hierarchical embodiment dataset based on BridgeV2, containing 60,000 robot manipulation trajectories auto-annotated with grounded task reasoning and spatial guidance. Additionally, we introduce a trajectory segmentation strategy based on gripper states and motion trajectories, which can help mitigate hallucination in grounding subtask reasoning generation. Experimental results demonstrate that Emma-X achieves superior performance over competitive baselines, particularly in real-world robotic tasks requiring spatial reasoning.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 14 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

13 of 14 references.

References · 13

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Segment Anythingcited by 8,158
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  10. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  11. 2024RT-H: Action Hierarchies Using Languagecited by 204
  12. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87
1 more
  1. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policycited by 51

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 24; 2026: 21.

45 papers.

Sort:

By area:

  1. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189
  2. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  3. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  5. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulationcited by 71
  6. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  7. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45
  8. 2025NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewardscited by 26
  9. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 26
  10. 2025Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoningcited by 22
  11. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  12. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
33 more
  1. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  2. 2025RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Modelcited by 16
  3. 2025Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresightcited by 12
  4. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 12
  5. 2025DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Actioncited by 11
  6. 2026MolmoPoint: Better Pointing for VLMs with Grounding Tokenscited by 11
  7. 2025ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learningcited by 10
  8. 2025PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligencecited by 10
  9. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  10. 2025Mind to Hand: Purposeful Robotic Control via Embodied Reasoningcited by 7
  11. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  12. 2026TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Modelscited by 7
  13. 2026TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patchescited by 5
  14. 2026ABot-N1: Toward a General Visual Language Navigation Foundation Modelcited by 5
  15. 2026DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoningcited by 4
  16. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 4
  17. 2025Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and Challengescited by 3
  18. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  19. 2026Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agentscited by 3
  20. 2025IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interactioncited by 2
  21. 2025FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulationcited by 2
  22. 202510 Open Challenges Steering the Future of Vision-Language-Action Modelscited by 2
  23. 2026Towards Predictive, Aligned, and Scalable Robot Learningcited by 2
  24. 2026JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignmentcited by 2
  25. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  26. 2025Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representationscited by 1
  27. 2026CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systemscited by 1
  28. 2026E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulationcited by 1
  29. 2026VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Predictioncited by 1
  30. 2025Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thoughtcited by 0
  31. 2026Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learningcited by 0
  32. 2026RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulationcited by 0
  33. 2026StenoVLA-3D: 3D-Aware Reasoning VLA for Navigation Through Gastrointestinal Stenosescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Igniting VLMs toward the Embodied Space
  2. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
  3. 2026Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
  4. 2026SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
  5. 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
  6. 2026HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
  7. 2026Spatially Grounded Long-Horizon Task Planning in the Wild
  8. 2026EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories