collaborators

9 papers

cs.CR2026

ContainmentBench: Trace-Based Evaluation of Post-Exposure Containment in Tool-Using LLM Agents

Wenhao Lan, Shan Li, Xinhua Lai +3

Tool-using large language model (LLM) agents read untrusted content, maintain memory, delegate tasks, and invoke tools with external side effects. Terminal attack-success or policy…

cs.CV2026

HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents

Hy Vision Team, Huawen Shen, Zhengyang Tang +20

The paper introduces HyMobileAgent, a vision-native mobile GUI agent that combines large multimodal models with a co-scaling framework for data and environments to enable precise p…

cs.CR2026

From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning

Wenhao Lan, Shan Li, Xinhua Lai +3

Safety alignment requires language models to refuse harmful requests without losing the ability to answer benign ones. Existing robustness evaluations, however, do not reveal wheth…

cs.CL2026

PhoneBuddy: Training Open Models for Agentic Phone Use

Zhengyang Tang, Xin Lai, Pengyuan Lyu +23

Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matter…

cs.CL2026

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

Chenxin Li, Zhengyao Fang, Zhengyang Tang +18

Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature sti…

cs.CL2026

PhoneWorld: Scaling Phone-Use Agent Environments

Zhengyang Tang, Yuxuan Liu, Xin Lai +21

A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks…