mlsanityData to 7 Oct 2026

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

arXiv 2601.09708 ↗First posted 14 Jan 2026cs.CV cs.AI cs.LGcited by 20

On the map: Vision-language-action models → Reasoning and chain-of-thought in VLA

Abstract (arXiv)

Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models. Builds on 70 of its 76 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

70 of 76 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification18 Oct
  2. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning22 Jul
  3. 2025Training Strategies for Efficient Embodied Reasoning13 May
  4. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  5. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul

Other references · 65

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  10. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  11. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  12. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
38 more
  1. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  3. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  4. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  7. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  8. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  9. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  10. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  11. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  12. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  13. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  14. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
  15. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  16. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 381
  17. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  18. 2025Training Language Models to Reason Efficientlycited by 242
  19. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  20. 2025CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillationcited by 216
  21. 2024NVILA: Efficient Frontier Visual Language Modelscited by 206
  22. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representationscited by 192
  23. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189
  24. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  25. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  26. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  27. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  28. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 136
  29. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concretecited by 134
  30. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulationcited by 125
  31. 2023RoboVQA: Multimodal Long-Horizon Reasoning for Roboticscited by 116
  32. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 110
  33. 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Spacecited by 109
  34. 2025RoboBrain 2.0 Technical Reportcited by 87
  35. 2025Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfercited by 86
  36. 2025Grounded Reinforcement Learning for Visual Reasoningcited by 80
  37. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 69
  38. 2023EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planningcited by 66

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Modelscited by 20
  2. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  3. 2026Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoningcited by 17
  4. 2026TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformerscited by 14
  5. 2026Long-Horizon Manipulation via Trace-Conditioned VLA Planningcited by 9
  6. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 4
  7. 2026Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulationcited by 4
  8. 2026CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Modelscited by 3
  9. 2026Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Modelscited by 3
  10. 2026Continuous Reasoning for Vision-Language-Actioncited by 2
  11. 2026SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videoscited by 2
  12. 2026Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulationcited by 1
8 more
  1. 2026Self-supervised Hierarchical Visual Reasoning with World Modelcited by 1
  2. 2026SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scalecited by 1
  3. 2026World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulationcited by 1
  4. 2026Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learningcited by 0
  5. 2026What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agentscited by 0
  6. 2026SCULPT-VLA: Learning Structured Control through Staged Action Groundingcited by 0
  7. 2026The Right Future for Action: Learning Action-Relevant Predictive States in World Action Modelscited by 0
  8. 2026GT-VLA: Target-Conditioned Trace Guidance for Generalizable Robotic Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
  2. 2026ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation
  3. 2025Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
  4. 2025MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoning
  5. 2026Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
  6. 2026PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
  7. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
  8. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection