mlsanityData to 7 Oct 2026

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models

arXiv 2511.01331 ↗First posted 3 Nov 2025cs.RO cs.LGcited by 16

On the map: Vision-language-action models → Reinforcement learning and post-training

Abstract (arXiv)

Vision-Language-Action (VLA) models have recently emerged as powerful general-purpose policies for robotic manipulation, benefiting from large-scale multi-modal pre-training. However, they often fail to generalize reliably in out-of-distribution deployments, where unavoidable disturbances such as observation noise, sensor errors, or actuation perturbations become prevalent. While recent Reinforcement Learning (RL)-based post-training provides a practical means to adapt pre-trained VLA models, existing methods mainly emphasize reward maximization and overlook robustness to environmental uncertainty. In this work, we introduce RobustVLA, a lightweight online RL post-training method designed to explicitly enhance the resilience of VLA models. Through a systematic robustness analysis, we identify two key regularizations: Jacobian regularization, which mitigates sensitivity to observation noise, and smoothness regularization, which stabilizes policies under action perturbations. Extensive experiments across diverse robotic environments demonstrate that RobustVLA significantly outperforms prior state-of-the-art methods in robustness and reliability. Our results highlight the importance of principled robustness-aware RL post-training as a key step toward improving the reliability and robustness of VLA models.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models. Builds on 52 of its 62 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

52 of 62 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation8 Aug
  2. 2025TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization10 Jun
  3. 2025What Can RL Bring to VLA Generalization? An Empirical Study26 May
  4. 2025RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback26 May
  5. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning24 May
  6. 2025Interactive Post-Training for Vision-Language-Action Models22 May
  7. 2025ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning12 May
  8. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy8 Feb
  9. 2025Improving Vision-Language-Action Model with Online Reinforcement Learning28 Jan
  10. 2024Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance17 Oct
  11. 2024Octo: An Open-Source Generalist Robot Policy20 May

Other references · 41

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  9. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  10. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  11. 2018Attention, Learn to Solve Routing Problems!cited by 646
  12. 2017Robust Adversarial Reinforcement Learningcited by 439
29 more
  1. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  2. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  3. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  4. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 129
  5. 2025GR-3 Technical Reportcited by 110
  6. 2025Reinforcement Learning for Long-Horizon Interactive LLM Agentscited by 103
  7. 2021Online Robust Reinforcement Learning with Model Uncertaintycited by 95
  8. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  9. 2019Corruption-robust exploration in episodic reinforcement learningcited by 72
  10. 2024Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbonecited by 71
  11. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  12. 2024FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuningcited by 54
  13. 2025ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrationscited by 52
  14. 2021Corruption-Robust Offline Reinforcement Learningcited by 51
  15. 2021A Model Selection Approach for Corruption Robust Reinforcement Learningcited by 45
  16. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learningcited by 42
  17. 2025H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulationcited by 41
  18. 2022Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processescited by 33
  19. 2024Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robustcited by 33
  20. 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulationcited by 26
  21. 2025Is Diversity All You Need for Scalable Robotic Manipulation?cited by 19
  22. 2025Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Modelscited by 14
  23. 2024Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruptioncited by 12
  24. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learningcited by 12
  25. 2023Safe Reinforcement Learning with Dual Robustnesscited by 10
  26. 2024To Err is Robotic: Rapid Value-Based Trial-and-Error during Deploymentcited by 7
  27. 2024ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learningcited by 5
  28. 2025Hybrid Cross-domain Robust Reinforcement Learningcited by 3
  29. 2025DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertaintycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 15.

16 papers.

Sort:

By area:

  1. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  2. 2026Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptationcited by 4
  3. 2026FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulationcited by 4
  4. 2026RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Modelscited by 3
  5. 2026Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faultscited by 2
  6. 2026Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learningcited by 2
  7. 2026Reflective VLA: In-Context Action Consequences Make VLAs Generalizecited by 1
  8. 2026What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Modelscited by 0
  9. 2026VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesiscited by 0
  10. 2026ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Modelscited by 0
  11. 2026Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Modelscited by 0
  12. 2026Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policycited by 0
4 more
  1. 2026Are Vision-Language-Action Models Robust to One-Step Observation Perturbations?cited by 0
  2. 2026Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testingcited by 0
  3. 2026RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulationcited by 0
  4. 2026CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
  2. 2026VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
  3. 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
  4. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
  5. 2025RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
  6. 2025VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
  7. 2025Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
  8. 2026Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models