activity
20242026
collaborators

6 papers

cs.AI2026

Agent Learning via Early Experience

Kai Zhang, Xiangchao Chen, Bo Liu +27

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents fro…

cs.CL2026

Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents

Tianci Xue, Zeyi Liao, Tianneng Shi +5

Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and distribution shifts, making conti…

cs.CL2026

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

Zeyi Liao, Jaylen Jones, Linxi Jiang +5

Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection. Current evaluations of t…

cs.HC2025

Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging

Zeyi Liao, Yadong Lu, Boyu Gou +2

Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding…

cs.CL2024

AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Zeyi Liao, Huan Sun

As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety…

cs.CL2024

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Vishal Kumar, Zeyi Liao, Jaylen Jones +1

Although large language models (LLMs) are typically aligned, they remain vulnerable to jailbreaking through either carefully crafted prompts in natural language or, interestingly,…