# VLA-R1: Enhancing Reasoning in Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2510.01623 · HTML: https://mlsanity.com/paper/2510.01623/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 37 of its 41 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 30 of 37)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates](https://mlsanity.com/paper/1610.00633/) (2016)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2312.16217/) (2023)
- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning](https://mlsanity.com/paper/2406.11815/) (2024)
- [End-to-End Affordance Learning for Robotic Manipulation](https://mlsanity.com/paper/2209.12941/) (2022)
- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks](https://mlsanity.com/paper/2503.21696/) (2025)
- [Nav-R1: Reasoning and Navigation in Embodied Scenes](https://mlsanity.com/paper/2509.10884/) (2025)
- [EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling](https://mlsanity.com/paper/2507.05198/) (2025)

## Built on by (most cited first, 30 of 38)

- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [LaST0: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model](https://mlsanity.com/paper/2601.05248/) (2026)
- [SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead](https://mlsanity.com/paper/2512.00903/) (2025)
- [Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation](https://mlsanity.com/paper/2601.01984/) (2026)
- [Scaling World Model for Hierarchical Manipulation Policies](https://mlsanity.com/paper/2602.10983/) (2026)
- [MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots](https://mlsanity.com/paper/2511.17889/) (2025)
- [TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers](https://mlsanity.com/paper/2601.14133/) (2026)
- [Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation](https://mlsanity.com/paper/2512.07472/) (2025)
- [EvoVLA: Self-Evolving Vision-Language-Action Model](https://mlsanity.com/paper/2511.16166/) (2025)
- [GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch](https://mlsanity.com/paper/2607.13960/) (2026)
- [LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning](https://mlsanity.com/paper/2604.28192/) (2026)
- [Towards a Theoretical Understanding to the Generalization of RLHF](https://mlsanity.com/paper/2601.16403/) (2026)
- [GeoWorld: Geometric World Models](https://mlsanity.com/paper/2602.23058/) (2026)
- [VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning](https://mlsanity.com/paper/2603.14523/) (2026)
- [One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy](https://mlsanity.com/paper/2605.07931/) (2026)
- [NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2607.06678/) (2026)
- [EgoLCD: Egocentric Video Generation with Long Context Diffusion](https://mlsanity.com/paper/2512.04515/) (2025)
- [AnyDepth: Depth Estimation Made Easy](https://mlsanity.com/paper/2601.02760/) (2026)
- [IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.20715/) (2026)
- [VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery](https://mlsanity.com/paper/2510.04479/) (2025)
- [Recursive Belief Vision Language Action Models](https://mlsanity.com/paper/2602.20659/) (2026)
- [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026)
- [Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2603.09740/) (2026)
- [CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts](https://mlsanity.com/paper/2606.31986/) (2026)
- [IRPO: Boosting Image Restoration via Post-training GRPO](https://mlsanity.com/paper/2512.00814/) (2025)
- [NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models](https://mlsanity.com/paper/2603.09542/) (2026)
- [Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models](https://mlsanity.com/paper/2606.31846/) (2026)
- [Panoramic Affordance Prediction](https://mlsanity.com/paper/2603.15558/) (2026)
- [Driving Intents Amplify Planning-Oriented Reinforcement Learning](https://mlsanity.com/paper/2605.12625/) (2026)
- [Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO](https://mlsanity.com/paper/2606.02313/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack explicit step-by-step reasoning, instead emitting final actions without considering affordance constraints or geometric relations. Their post-training pipelines also rarely reinforce reasoning quality, relying primarily on supervised fine-tuning with weak reward design. To address these challenges, we present VLA-R1, a reasoning-enhanced VLA that integrates Reinforcement Learning from Verifiable Rewards (RLVR) with Group Relative Policy Optimization (GRPO) to systematically optimize both reasoning and execution. Specifically, we design an RLVR-based post-training strategy with verifiable rewards for region alignment, trajectory consistency, and output formatting, thereby strengthening reasoning robustness and execution accuracy. Moreover, we develop VLA-CoT-13K, a high-quality dataset that provides chain-of-thought supervision explicitly aligned with affordance and trajectory annotations. Furthermore, extensive evaluations on in-domain, out-of-domain, simulation, and real-robot platforms demonstrate that VLA-R1 achieves superior generalization and real-world performance compared to prior VLA methods. We plan to release the model, code, and dataset following the publication of this work. Code: https://github.com/GigaAI-research/VLA-R1. Website: https://gigaai-research.github.io/VLA-R1.