# Training Strategies for Efficient Embodied Reasoning

arXiv: https://arxiv.org/abs/2505.08243 · HTML: https://mlsanity.com/paper/2505.08243/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 54 of its 64 references that are in the map.
- First posted on arXiv 13 May 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 54)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [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)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (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)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (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)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [Think before you speak: Training Language Models With Pause Tokens](https://mlsanity.com/paper/2310.02226/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Chain of Thought Empowers Transformers to Solve Inherently Serial Problems](https://mlsanity.com/paper/2402.12875/) (2024)
- [Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets](https://mlsanity.com/paper/2109.13396/) (2021)
- [Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?](https://mlsanity.com/paper/2303.18240/) (2023)

## Built on by (most cited first, 30 of 55)

- [SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning](https://mlsanity.com/paper/2509.09674/) (2025)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning](https://mlsanity.com/paper/2505.11917/) (2025)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models](https://mlsanity.com/paper/2606.17846/) (2026)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization](https://mlsanity.com/paper/2510.25616/) (2025)
- [Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories](https://mlsanity.com/paper/2607.15330/) (2026)
- [Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification](https://mlsanity.com/paper/2510.16281/) (2025)
- [Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey](https://mlsanity.com/paper/2510.17111/) (2025)
- [Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning](https://mlsanity.com/paper/2601.09708/) (2026)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models](https://mlsanity.com/paper/2602.01166/) (2026)
- [GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions](https://mlsanity.com/paper/2508.07650/) (2025)
- [DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models](https://mlsanity.com/paper/2511.15669/) (2025)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models](https://mlsanity.com/paper/2603.22003/) (2026)
- [Thinking in 360deg: Humanoid Visual Search in the Wild](https://mlsanity.com/paper/2511.20351/) (2025)
- [Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation](https://mlsanity.com/paper/2511.19859/) (2025)
- [CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2601.02295/) (2026)
- [Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight](https://mlsanity.com/paper/2511.16175/) (2025)
- [PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies](https://mlsanity.com/paper/2509.18282/) (2025)
- [DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action](https://mlsanity.com/paper/2511.22134/) (2025)
- [SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios](https://mlsanity.com/paper/2602.08440/) (2026)
- [Flex-π: A Multi-Stream World-Action Model with Compute Flexibility](https://mlsanity.com/paper/2608.10860/) (2026)
- [Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots](https://mlsanity.com/paper/2511.00917/) (2025)
- [Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models](https://mlsanity.com/paper/2512.01946/) (2025)
- [Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision](https://mlsanity.com/paper/2606.30552/) (2026)
- [Survey of Vision-Language-Action Models for Embodied Manipulation](https://mlsanity.com/paper/2508.15201/) (2025)

## Abstract (arXiv)

Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially vision-language-action models (VLAs). While such approaches have been shown to improve performance and generalization, they suffer from core limitations, like needing specialized robot reasoning data and slow inference speeds. To design new robot reasoning approaches that address these issues, a more complete characterization of why reasoning helps policy performance is critical. We hypothesize several mechanisms by which robot reasoning improves policies -- (1) better representation learning, (2) improved learning curricularization, and (3) increased expressivity -- then devise simple variants of robot CoT reasoning to isolate and test each one. We find that learning to generate reasonings does lead to better VLA representations, while attending to the reasonings aids in actually leveraging these features for improved action prediction. Our results provide us with a better understanding of why CoT reasoning helps VLAs, which we use to introduce two simple and lightweight alternative recipes for robot reasoning. Our proposed approaches achieve significant performance gains over non-reasoning policies, state-of-the-art results on the LIBERO-90 benchmark, and a 3x inference speedup compared to standard robot reasoning.