Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models

cs.RO, cs.CL, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: 9 pages, 8 figures, 3 tables. Project page: https://sttawm.github.io/rephrase-before-you-act

Code: https://github.com/sttawm/vla-rephrasing-artifacts

Project page: https://sttawm.github.io/rephrase-before-you-act

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
• Adapting Generalist Robot Policies with Semantic Reinforcement Learning
• VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
• LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• Embodied Red Teaming for Auditing Robotic Foundation Models
• Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy
• Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
• Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering
• Qwen3 Technical Report

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies