conftrace_

computer-use agent

4 papers

Explore in graph

Also known as

CUA

Co-occurring keywords · papers mentioning both

vision-language model (2) safety bypass (1) expert trajectory (1) step-level filtering (1) reinforcement learning from verifiable reward (1) multimodal reward model (1) language model security (1) capability evaluation (1) reasoning augmentation (1) prompt injection (1)

Papers

From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation ACL 2026 Towards Capable and Secure Autonomous Computer-Use Agents (Student Abstract) AAAI 2026 WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering ACL 2026 sudo rm -rf agentic_security ACL 2025