collaborators

5 papers

cs.CR2026

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

Shijing Hu, Liang Liu, Zhu Meng +1

Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks…

cs.CL2026

Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis

Songze Li, Yarong Lan, Zhongpu Bo +16

Knowledge injection via synthetic data is crucial for enhancing Large Language Models (LLMs). However, current synthesis methods simply stop at preset token counts or fixed data ra…

cs.HC2026

MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization

Guangyi Liu, Pengxiang Zhao, Gao Wu +9

MLLM-based mobile GUI agents have made substantial progress in UI understanding and action execution, but adapting them to real target apps remains costly because mobile apps are n…

cs.HC2026

MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management

Guangyi Liu, Gao Wu, Congxiao Liu +7

MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across man…

cs.DC2026

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

Guangyi Liu, Pengxiang Zhao, Yaozhen Liang +12

Reliable mobile GUI agents must retain and reuse information across actions, applications, and repeated interactions. However, current benchmarks systematically underrepresent thes…