# DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2511.15669 · HTML: https://mlsanity.com/paper/2511.15669/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 52 of its 66 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 30 of 52)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot](https://mlsanity.com/paper/2307.00595/) (2023)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation](https://mlsanity.com/paper/2412.13877/) (2024)

## Built on by (most cited first, 18 of 18)

- [Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models](https://mlsanity.com/paper/2602.01166/) (2026)
- [DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2603.22280/) (2026)
- [Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision](https://mlsanity.com/paper/2606.30552/) (2026)
- [VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning](https://mlsanity.com/paper/2603.14523/) (2026)
- [TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches](https://mlsanity.com/paper/2603.23117/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies](https://mlsanity.com/paper/2605.30011/) (2026)
- [SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning](https://mlsanity.com/paper/2602.00743/) (2026)
- [SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models](https://mlsanity.com/paper/2609.05533/) (2026)
- [SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models](https://mlsanity.com/paper/2603.24935/) (2026)
- [Continuous Reasoning for Vision-Language-Action](https://mlsanity.com/paper/2606.00229/) (2026)
- [Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation](https://mlsanity.com/paper/2603.12717/) (2026)
- [Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks](https://mlsanity.com/paper/2604.09028/) (2026)
- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation](https://mlsanity.com/paper/2606.06836/) (2026)
- [ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2606.17937/) (2026)
- [Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models](https://mlsanity.com/paper/2607.17786/) (2026)
- [When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies](https://mlsanity.com/paper/2610.00601/) (2026)

## Abstract (arXiv)

Does Chain-of-Thought (CoT) reasoning genuinely improve Vision Language Action (VLA) models, or does it merely add overhead? Existing CoT-VLA systems report limited and inconsistent gains, yet no prior work has rigorously diagnosed when and why CoT helps robots act. Through systematic experiments, we identify two necessary conditions that must be jointly satisfied for CoT to be effective in VLA: (1) Decoding Alignment: CoT and actions must be generated with modality-appropriate mechanisms; forcing both through a single autoregressive decoder is not merely suboptimal but actively harmful, degrading performance by 4.2 percentage points; (2) Causal Alignment: CoT must be causally linked to task success via outcome-based optimization; without it, supervised CoT is indistinguishable from no reasoning at all under action-execution-sensitive dynamics shift, exhibiting a 32.0 pp performance drop nearly identical to the 31.6 pp drop of a reasoning-free baseline. Guided by these findings, we build DeepThinkVLA: a hybrid-attention decoder satisfies Condition 1 by pairing causal attention for language with bidirectional attention for parallel action decoding, while a two-stage SFT-then-RL pipeline satisfies Condition 2 by aligning the full reasoning: action chain with sparse task-success rewards. DeepThinkVLA achieves 97.0% success on LIBERO, 79.0% robustness on LIBERO-Plus (vs. 61.6% for π0-FAST), and 59.3% success on RoboTwin 2.0, exceeding the strongest baseline by 21.7 points. Furthermore, real-robot experiments provide preliminary evidence for the physical applicability of our CoT data construction and hybrid architecture. Our codes are available at https://github.com/OpenBMB/DeepThinkVLA.