MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Wenqi, Shen, Yulin, Jiang, Changyue, Dai, Jiarun, Hong, Geng, Pan, Xudong
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.12822