mlsanityData to 14 Oct 2026

TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

arXiv 2610.17540 ↗First posted 13 Oct 2026cs.AI cs.ROcited by 0

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

Abstract (arXiv)

Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding. We show that actions do not need to wait for or condition on the generated reasoning to benefit from it, because the reasoning supervision already improves the backbone representation. We introduce TacitVLA, a reasoning VLA whose action expert never attends to the reasoning it generates for the current call. On long-horizon tasks where the reasoning text also serves as episodic memory, it can generate each entry during action execution rather than before acting. We evaluate it in a controlled study on four benchmarks spanning manipulation and autonomous driving, memory and non-memory tasks: RoboMME, RMBench, LIBERO, and PhysicalAI-AV. On all four, TacitVLA matches the performance of its explicit-reasoning counterpart at up to 3.4x lower latency, and matches the latency of the same architecture trained without reasoning at up to +17.1% success. In absolute terms, it surpasses the best previously published results on the RoboMME Counting suite (82.7% vs. 66.8%) and RMBench (77.5% vs. 56.5%), and reaches 72.9% on LIBERO-Plus and a 52.5% scene score on the public split of the PhysicalAI-AV closed-loop driving challenge. Project page: https://tacitvla.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models. Builds on 48 of its 57 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

48 of 57 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies30 Aug
  2. 2026EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies18 Jun
  3. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation2 Jun
  4. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies4 Mar
  5. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models1 Feb
  6. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning14 Jan
  7. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation26 Aug
  8. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning22 Jul
  9. 2025Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse9 Jun
  10. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning17 May
  11. 2025Training Strategies for Efficient Embodied Reasoning13 May
  12. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul

Other references · 36

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  7. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  8. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  9. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 349
  10. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  11. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  12. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
24 more
  1. 2023Implicit Chain of Thought Reasoning via Knowledge Distillationcited by 176
  2. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 163
  3. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 146
  4. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  5. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 117
  6. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 103
  7. 2025VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Cachingcited by 86
  8. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformerscited by 75
  9. 2025SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulationcited by 61
  10. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 36
  11. 2025VaViM and VaVAM: Autonomous Driving through Video Generative Modelingcited by 35
  12. 2025MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agentcited by 18
  13. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 16
  14. 2026MemoryWAM: Efficient World Action Modeling with Persistent Memorycited by 13
  15. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesiscited by 12
  16. 2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervisioncited by 8
  17. 2026Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmentcited by 6
  18. 2026World Pilot: Steering Vision-Language-Action Models with World-Action Priorscited by 3
  19. 2026FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Modelscited by 3
  20. 2026VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Expertscited by 2
  21. 2026ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptationcited by 2
  22. 2026Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Modelscited by 2
  23. 2026LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Modelscited by 1
  24. 2026HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
  2. 2026Continuous Reasoning for Vision-Language-Action
  3. 2026VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
  4. 2026In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use
  5. 2026Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
  6. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Action
  7. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
  8. 2026Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models