RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors
cs.RO, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models
- CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation
- Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents
- Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention
- Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
- PREFAIL: Identifying Precursors to Failures in Robotic Lift-and-Place Tasks to Improve Task Execution Performance
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- AEGIS: A Backup Reflex for Physical AI
- Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection
- Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning
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