Safety Evaluation of VLAs

VLA: Vision-Language-Action Model

Overview

This field tests whether robots and driving agents can interpret instructions and act safely in interactive environments. Benchmarks use matched safe and unsafe scenarios, trajectory-level safety rules, counterfactual tests, and simulation-to-physical evaluation to separate safe behavior from task completion. Methods include adversarial red teaming, runtime action screening and abstention, semantic guards, robustness checks, and safety-aware training. Strong hazard recognition or task success often fails to ensure safe execution, leaving open challenges in cross-domain generalization, standardized metrics, and balancing safety with useful performance.

Latest papers

CardsList

41 papers14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

  1. SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models

    May 30, 2026Jialiang Fan, Weizhe Xu, Zijun Wang +3Robot SafetyRobotic Manipulation

  2. ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

    May 27, 2026Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1VLMs for Autonomous DrivingAutonomous Driving Safety Evaluation

  3. Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts

    May 21, 2026Zhen Sun, Yongjian Guo, Haoran Sun +6Vision-Language-Action ModelsVLMs for Robotics

  4. Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

    Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6AI Agent SafetyAdversarial Attacks on VLAs

  5. RedVLA: Physical Red Teaming for Vision-Language-Action Models

    Apr 24, 2026Yuhao Zhang, Borong Zhang, Jiaming Fan +4RoboticsAdversarial Attacks on VLAs

  6. How VLAs (Really) Work In Open-World Environments

    Apr 23, 2026Amir Rasouli, Yangzheng Wu, Zhiyuan Li +4VLM RobustnessLong-Horizon Robotic Manipulation

  7. SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

    Apr 21, 2026Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5Safety Evaluation of VLAsLLM Safety Benchmarks

  8. HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

    Apr 14, 2026Zixing Chen, Yifeng Gao, Li Wang +8RoboticsAI Safety Evaluation

  9. Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

    Apr 7, 2026Baoshun Tong, Haoran He, Ling Pan +2Adversarial Attacks on VLAsRobustness of VLAs

  10. Safety Case Patterns for VLA-based driving systems: Insights from SimLingo

    Mar 16, 2026Gerhard Yu, Fuyuki Ishikawa, Oluwafemi Odu +1Autonomous Driving Safety EvaluationAutonomous Driving