paper-with-me

Papers

UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents

2026-05-28 · Yuxiang Chai, Han Xiao, Xinyu Fu, Jinpeng Chen, Rui Liu, Hongsheng Li arxiv

Recent advances in mobile GUI agents have shown strong potential for automating mobile tasks, but most effective systems still depend on large vision-language models for screenshot understanding and long-horizon planning. Small GUI agents that can be deployed directly on mobile devices are more attractive for practical use, offering lower inference cost and better protection of sensitive on-device information. However, due to limited model capacity, such lightweight agents remain unreliable when planning and executing GUI tasks end-to-end from screenshots alone. We propose Knowledge-Oriented Behavior Exploration (\textbf{UI-KOBE}), a framework that improves lightweight mobile GUI agents with reusable app-specific graph knowledge. UI-KOBE first autonomously explores a mobile application and constructs an app knowledge graph, where nodes represent distinct UI states and edges represent executable transitions. At runtime, a lightweight GUI agent uses the graph as external guidance: given a user task and the current screenshot, it identifies the current graph node and selects among self-loop actions, neighboring transitions, task completion, or fallback free actions associated with that node. By supporting runtime decisions with app-specific graph guidance, UI-KOBE reduces the burden of end-to-end GUI planning and helps lightweight models perform mobile GUI tasks more effectively, offering a practical step toward efficient, interpretable, and privacy-conscious on-device GUI agents.

📄 PDF Abstract BibTeX arXiv:2605.29534

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Knowledge-Based Personalized Product Description Generation in E-commerce

2019-03-29 · Qibin Chen, Junyang Lin, Yichang Zhang, Hongxia Yang 외

Quality product descriptions are critical for providing competitive customer experience in an e-commerce platform. An accurate and attractive description not only helps customers make an informed decision but also improv…

Text Generation

Entropy-Based Observability for AI Agent Behavior

2026-06-04 · Olasimbo Ayodeji Arigbabu arxiv

AI agents are typically instrumented through outcome-oriented indicators such as task success, reward, latency, and cost.Although these indicators are operationally important, they provide limited visibility into the int…

KOBEST: Korean Balanced Evaluation of Significant Tasks

2022-04-09 · COLING 2022 10 · Dohyeong Kim, Myeongjun Jang, Deuk Sin Kwon, Eric Davis

A well-formulated benchmark plays a critical role in spurring advancements in the natural language processing (NLP) field, as it allows objective and precise evaluation of diverse models. As modern language models (LMs) …

BEAC: Imitating Complex Exploration and Task-oriented Behaviors for Invisible Object Nonprehensile Manipulation

2025-03-21 · Hirotaka Tahara, Takamitsu Matsubara

Applying imitation learning (IL) is challenging to nonprehensile manipulation tasks of invisible objects with partial observations, such as excavating buried rocks. The demonstrator must make such complex action decision…

Imitation Learning

IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models

2024-06-05 · David Ifeoluwa Adelani, Jessica Ojo, Israel Abebe Azime, Jian Yun Zhuang 외

Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (\eg African languages) are often …

Mathematical ReasoningNatural Language InferenceQuestion Answeringtext-classification+1