2 papers
cs.CL2026
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
Yuzhe Zhang, Xianwei Xue, Xingyong Wu +8
Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succ…
cs.RO2026
ROVER: Regulator-Driven Robust Temporal Verification of Black-Box Robot Policies
Kristy Sakano, Jianyu An, Dinesh Manocha +1
We present a novel, regulator-driven approach for the temporal verification of black-box autonomous robot policies, inspired by real-world certification processes where regulators…