# Failure recovery and robustness Area: [Vision-language-action models](https://mlsanity.com/vla/index.md). HTML: https://mlsanity.com/vla/failure-recovery-and-robustness/ ## Key facts - Failure recovery and robustness: 109 papers on arXiv since 2025 (data through 7 Oct 2026). - 26 of its 109 mapped papers (24%) cite “LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models” (2025, arXiv 2510.13626). - 20 of its 109 mapped papers (18%) cite “SAFE: Multitask Failure Detection for Vision-Language-Action Models” (2025, arXiv 2506.09937). - 36 new papers 17 Sep–7 Oct. ## Most cited here - [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025), cited by 26 papers here - [SAFE: Multitask Failure Detection for Vision-Language-Action Models](https://mlsanity.com/paper/2506.09937/) (2025), cited by 20 papers here - [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025), cited by 18 papers here - [FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01642/) (2025), cited by 11 papers here - [RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction](https://mlsanity.com/paper/2505.12224/) (2025), cited by 7 papers here - [Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots](https://mlsanity.com/paper/2507.17049/) (2025), cited by 7 papers here - [CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2601.02295/) (2026), cited by 5 papers here - [When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs](https://mlsanity.com/paper/2602.17659/) (2026), cited by 5 papers here - [FPC-VLA: A Vision-Language-Action Framework with a Supervisor for Failure Prediction and Correction](https://mlsanity.com/paper/2509.04018/) (2025), cited by 4 papers here - [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026), cited by 4 papers here ## New (17 Sep–7 Oct) - [Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models](https://mlsanity.com/paper/2610.09496/) (2026-10-07) - [Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?](https://mlsanity.com/paper/2610.09170/) (2026-10-06) - [CARE: Certifying Acceleration for Vision-Language-Action Inference](https://mlsanity.com/paper/2610.08917/) (2026-10-06) - [Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution](https://mlsanity.com/paper/2610.07946/) (2026-10-06) - [When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models](https://mlsanity.com/paper/2610.05719/) (2026-10-05) - [A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.05166/) (2026-10-04) - [Does a Learned Corrector Beat a Simple Retreat? Evidence from a Frozen VLA](https://mlsanity.com/paper/2610.06921/) (2026-10-02) - [SocialVLA: A Social Perception Gateway for Human-Reaction-Based Failure Detection and Recovery in VLA Manipulation](https://mlsanity.com/paper/2610.02360/) (2026-10-01) - [Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks](https://mlsanity.com/paper/2610.01351/) (2026-10-01) - [MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation](https://mlsanity.com/paper/2610.00604/) (2026-09-30) - [When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models](https://mlsanity.com/paper/2609.39971/) (2026-09-30) - [Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models](https://mlsanity.com/paper/2609.39820/) (2026-09-30) - [Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults](https://mlsanity.com/paper/2609.39145/) (2026-09-30) - [Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents](https://mlsanity.com/paper/2609.37810/) (2026-09-29) - [Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration](https://mlsanity.com/paper/2609.37771/) (2026-09-29) - [Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing](https://mlsanity.com/paper/2609.37334/) (2026-09-29) - [Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence](https://mlsanity.com/paper/2609.35432/) (2026-09-28) - [Do Not Cut When Uncertain: Rejectable and Calibrated Decision Heads for VLA Policies in Robotic Harvesting](https://mlsanity.com/paper/2609.35039/) (2026-09-28) - [Learning to Act under Visual Interruptions with Vision-Language-Action Models](https://mlsanity.com/paper/2609.35003/) (2026-09-28) - [Natural State-Prediction Accuracy can Hide Weak Controlled Responsiveness in VLA Readouts](https://mlsanity.com/paper/2609.34684/) (2026-09-28) - [Gaze Prompts: Temporally Dense Human Attention for Vision-Language-Action Fine-Tuning](https://mlsanity.com/paper/2609.34550/) (2026-09-28) - [FailPatch: Failure Residual Patching for Vision-Language-Action Models](https://mlsanity.com/paper/2609.34175/) (2026-09-28) - [SEES: A Self-Evolving Embodied System via Failure-Guided VLA Policy Adaptation](https://mlsanity.com/paper/2609.32698/) (2026-09-26) - [ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts](https://mlsanity.com/paper/2609.31792/) (2026-09-25) - [Kintsugi-VLA: Turning Failed Robot Rollouts into Recovery Data through Interventional Recoverability](https://mlsanity.com/paper/2609.31048/) (2026-09-25) - [Causeway: Restoring Task Accessibility for Instruction Switching in VLA Policies](https://mlsanity.com/paper/2609.30913/) (2026-09-25) - [AdaHVLA: Adaptive Harnesses for Long-Horizon Vision-Language-Action Execution](https://mlsanity.com/paper/2609.29204/) (2026-09-24) - [Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation](https://mlsanity.com/paper/2609.26672/) (2026-09-22) - [IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models](https://mlsanity.com/paper/2609.25562/) (2026-09-22) - [CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.24118/) (2026-09-21)