5 papers
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…
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…
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…
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…
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…