mlsanityData to 7 Oct 2026

Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse

arXiv 2506.07639 ↗First posted 9 Jun 2025cs.ROcited by 20

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces significant inference latency, limiting real-time deployment. We propose Fast ECoT, an inference-time acceleration method that exploits the structured and repetitive nature of ECoT to (1) cache and reuse high-level reasoning across timesteps and (2) parallelise the generation of modular reasoning steps. Additionally, we introduce an asynchronous scheduler that decouples reasoning from action decoding, further boosting responsiveness. Fast ECoT requires no model changes or additional training and integrates easily into existing VLA pipelines. Experiments in both simulation (LIBERO) and real-world robot tasks show up to a 7.5% reduction in latency with comparable or improved task success rate and reasoning faithfulness, bringing ECoT policies closer to practical real-time deployment.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 3 of its 46 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

3 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar

Other references · 2

  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 10.

20 papers.

Sort:

By area:

  1. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  3. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  4. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  5. 2025LLaDA-VLA: Vision Language Diffusion Action Modelscited by 30
  6. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  7. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  8. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 12
  9. 2025DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Actioncited by 11
  10. 2025Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Groundingcited by 10
  11. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  12. 2026TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Controlcited by 5
8 more
  1. 2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoningcited by 5
  2. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  3. 2026VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policiescited by 4
  4. 2026Self-supervised Hierarchical Visual Reasoning with World Modelcited by 1
  5. 2026Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policiescited by 1
  6. 2026Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Modelscited by 0
  7. 2026DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?cited by 0
  8. 2026Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
  2. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
  3. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
  4. 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
  5. 2026Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
  6. 2026Accelerating Structured Chain-of-Thought in Autonomous Vehicles
  7. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
  8. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models