4 papers
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Yong Du, Tongbo Chen, Zhengxi Lu +5
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards,…
HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents
Tongbo Chen, Junbo Niu, Zhengxi Lu +8
Computer use agents (CUAs) have demonstrated strong capabilities in completing digital tasks. However, existing CUAs either rely solely on graphical user interface (GUI) interactio…
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Jiawei Chen, Ruoxi Xu, Boxi Cao +11
The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenar…
KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation
Tongbo Chen, Zhengxi Lu, Zhan Xu +13
Personalized mobile agents that infer user preferences and calibrate proactive assistance hold great promise as everyday digital assistants, yet existing benchmarks fail to capture…