activity
20242026
collaborators

10 papers

cs.AI2026

CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications

Linqiang Guo, Li Gu, Zihuan Jiang +8

Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without…

cs.AI2026

Benchmarking LLM Judges for Mobile Agent Evaluation

Ziqiang Wang, Ziqiang Wan, Li Gu +5

Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajectories remains largely unexamin…

cs.SE2026

Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?

Li Gu, Zihuan Jiang, Linqiang Guo +6

Recent advances in mobile agents are dominated by the GUI paradigm, in which agents perceive UI information and emit screen interactions. However, mobile platforms also expose a co…

cs.CV2026

PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery

Weidong Tang, Bohan Zhang, Zhixiang Chi +3

On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an online streaming sequence. Ex…

cs.CL2026

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

Yangfan Wang, Tianyang Sun, Chen Tang +3

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing app…

cs.CV2026

Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery

Bohan Zhang, Weidong Tang, Zhixiang Chi +4

On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known c…